Open Source Computer Vision Library https://opencv.org/
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

3012 lines
109 KiB

// This file is part of OpenCV project.
// It is subject to the license terms in the LICENSE file found in the top-level directory
// of this distribution and at http://opencv.org/license.html.
// Copyright (C) 2018-2019, Intel Corporation, all rights reserved.
// Third party copyrights are property of their respective owners.
#include "test_precomp.hpp"
#include "npy_blob.hpp"
#include <opencv2/dnn/shape_utils.hpp>
#include <numeric>
namespace opencv_test { namespace {
void yoloPostProcessing(
std::vector<Mat>& outs,
std::vector<int>& keep_classIds,
std::vector<float>& keep_confidences,
std::vector<Rect2d>& keep_boxes,
float conf_threshold,
float iou_threshold,
const std::string& test_name);
template<typename TString>
static std::string _tf(TString filename, bool required = true)
{
return findDataFile(std::string("dnn/onnx/") + filename, required);
}
class Test_ONNX_layers : public DNNTestLayer
{
public:
bool required;
Test_ONNX_layers() : required(true) { }
enum Extension
{
npy,
pb
};
void testInputShapes(const Net& net, const std::vector<Mat>& inps)
{
std::vector<MatShape> inLayerShapes;
std::vector<MatShape> outLayerShapes;
net.getLayerShapes(MatShape(), 0, inLayerShapes, outLayerShapes);
ASSERT_EQ(inLayerShapes.size(), inps.size());
for (int i = 0; i < inps.size(); ++i) {
bool hasDynamicShapes = inLayerShapes[i].empty();
if (hasDynamicShapes)
continue;
if (inLayerShapes[i].size() == 1) { // 1D input
ASSERT_EQ(shape(inLayerShapes[i][0], 1), shape(inps[i]));
} else {
// Compare all axes except batch dimension which is variable.
inLayerShapes[i][0] = inps[i].size[0];
ASSERT_EQ(inLayerShapes[i], shape(inps[i]));
}
}
}
void testONNXModels(const String& basename, const Extension ext = npy,
double l1 = 0, double lInf = 0, const bool useSoftmax = false,
bool checkNoFallbacks = true, int numInps = 1,
bool testShapes = true, bool useWinograd = true)
{
String onnxmodel = _tf("models/" + basename + ".onnx", required);
std::vector<Mat> inps(numInps);
Mat ref;
if (ext == npy) {
for (int i = 0; i < numInps; ++i)
inps[i] = blobFromNPY(_tf("data/input_" + basename + (numInps > 1 ? format("_%d", i) : "") + ".npy"));
ref = blobFromNPY(_tf("data/output_" + basename + ".npy"));
}
else if (ext == pb) {
for (int i = 0; i < numInps; ++i)
inps[i] = readTensorFromONNX(_tf("data/input_" + basename + (numInps > 1 ? format("_%d", i) : "") + ".pb"));
ref = readTensorFromONNX(_tf("data/output_" + basename + ".pb"));
}
else
CV_Error(Error::StsUnsupportedFormat, "Unsupported extension");
checkBackend(&inps[0], &ref);
Net net = readNetFromONNX(onnxmodel);
ASSERT_FALSE(net.empty());
if (testShapes)
testInputShapes(net, inps);
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
net.enableWinograd(useWinograd);
std::vector<String> inputNames;
for (int i = 0; i < numInps; ++i)
inputNames.push_back(format("%d", i));
net.setInputsNames(inputNames);
for (int i = 0; i < numInps; ++i)
net.setInput(inps[i], inputNames[i]);
Mat out = net.forward("");
if (useSoftmax)
{
LayerParams lp;
Net netSoftmax;
netSoftmax.addLayerToPrev("softmaxLayer", "Softmax", lp);
netSoftmax.setPreferableBackend(DNN_BACKEND_OPENCV);
netSoftmax.setInput(out);
out = netSoftmax.forward();
netSoftmax.setInput(ref);
ref = netSoftmax.forward();
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL)
{
l1 = std::max(l1, 1.4e-3);
lInf = std::max(lInf, 8e-3);
}
normAssert(ref, out, basename.c_str(), l1 ? l1 : default_l1, lInf ? lInf : default_lInf);
if (checkNoFallbacks)
expectNoFallbacksFromIE(net);
}
};
TEST_P(Test_ONNX_layers, InstanceNorm)
{
if (target == DNN_TARGET_MYRIAD)
testONNXModels("instancenorm", npy, 0, 0, false, false);
else
testONNXModels("instancenorm", npy);
}
TEST_P(Test_ONNX_layers, MaxPooling)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_GE(2020020000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("maxpooling", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, MaxPooling_2)
{
testONNXModels("two_maxpooling", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, Convolution)
{
testONNXModels("convolution");
testONNXModels("conv_asymmetric_pads");
}
TEST_P(Test_ONNX_layers, Convolution_variable_weight)
{
if ((backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH ||
backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019) && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA); // not supported
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN); // not supported
String basename = "conv_variable_w";
Net net = readNetFromONNX(_tf("models/" + basename + ".onnx"));
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
for (int i = 0; i < 2; i++)
{
Mat input = blobFromNPY(_tf("data/input_" + basename + format("_%d", i) + "_0.npy"));
Mat weights = blobFromNPY(_tf("data/input_" + basename + format("_%d", i) + "_1.npy"));
Mat ref = blobFromNPY(_tf("data/output_" + basename + format("_%d", i) + ".npy"));
net.setInput(input, "0");
net.setInput(weights, "1");
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
}
}
TEST_P(Test_ONNX_layers, Convolution_variable_weight_bias)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// openvino/src/plugins/intel_myriad/common/src/ngraph/transformations/extract_dynamic_batch/slice_convolution.cpp:14 Expecting operation v1::GroupConvolution GroupConvolution_6904725 (Reshape_17[0]:f32{1,4,5,5}, Reshape_6904719[0]:f32{4,1,1,2,2}) -> (f32{1,4,4,4}) to have constant kernel, got Reshape_6904719[0]:f32{4,1,1,2,2}
// openvino\src\plugins\intel_myriad\common\src\ngraph\transformations\extract_dynamic_batch\slice_convolution.cpp:15 Expecting operation v1::GroupConvolution GroupConvolution_6904692 (Reshape_17[0]:f32{1,4,5,5}, Reshape_6904686[0]:f32{4,1,1,2,2}) -> (f32{1,4,4,4}) to have constant kernel, got Reshape_6904686[0]:f32{4,1,1,2,2}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
// accuracy (depends on OpenCL version / HW)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#elif defined(INF_ENGINE_RELEASE)
if ((backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH ||
backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019) && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_CPU &&
getInferenceEngineCPUType() == CV_DNN_INFERENCE_ENGINE_CPU_TYPE_ARM_COMPUTE)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_ARM_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA); // supports only <= 2 inputs
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN); // not supported
String basename = "conv_variable_wb";
Net net = readNetFromONNX(_tf("models/" + basename + ".onnx"));
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
for (int i = 0; i < 2; i++)
{
Mat input = blobFromNPY(_tf("data/input_" + basename + format("_%d", i) + "_0.npy"));
Mat weights = blobFromNPY(_tf("data/input_" + basename + format("_%d", i) + "_1.npy"));
Mat bias = blobFromNPY(_tf("data/input_" + basename + format("_%d", i) + "_2.npy"));
Mat ref = blobFromNPY(_tf("data/output_" + basename + format("_%d", i) + ".npy"));
net.setInput(input, "0");
net.setInput(weights, "1");
net.setInput(bias, "bias");
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
}
}
TEST_P(Test_ONNX_layers, Gather)
{
testONNXModels("gather", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, Gather_Scalar)
{
testONNXModels("gather_scalar", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, GatherMulti)
{
// GPU plugin unsupported slice for constant
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
testONNXModels("gather_multi", npy, 0, 0, false, false);
}
1 year ago
TEST_P(Test_ONNX_layers, Gather_shared_indices) {
testONNXModels("gather_shared_indices", npy, 0, 0, false, false, 1);
}
TEST_P(Test_ONNX_layers, Two_resizes_with_shared_subgraphs) {
testONNXModels("two_resizes_with_shared_subgraphs", npy, 0, 0, false, false, 3, /*testShapes*/ false);
}
TEST_P(Test_ONNX_layers, Convolution3D)
{
if (backend == DNN_BACKEND_CUDA && target == DNN_TARGET_CUDA_FP16)
{
// CUDA_FP16: cuDNN did not return a suitable algorithm for convolution.
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA_FP16);
}
testONNXModels("conv3d");
}
TEST_P(Test_ONNX_layers, Convolution3D_bias)
{
if (backend == DNN_BACKEND_CUDA && target == DNN_TARGET_CUDA_FP16)
{
// CUDA_FP16: cuDNN did not return a suitable algorithm for convolution.
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA_FP16);
}
testONNXModels("conv3d_bias");
testONNXModels("conv3d_depthwise_bias"); // kernel 1x1
}
TEST_P(Test_ONNX_layers, Two_convolution)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD
&& getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X
)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
#endif
// Reference output values are in range [-0.855, 0.611]
testONNXModels("two_convolution");
}
TEST_P(Test_ONNX_layers, Deconvolution)
{
testONNXModels("deconvolution", npy, 0, 0, false, false);
testONNXModels("two_deconvolution", npy, 0, 0, false, false);
testONNXModels("deconvolution_group", npy, 0, 0, false, false);
testONNXModels("deconvolution_output_shape", npy, 0, 0, false, false);
if (target != DNN_TARGET_CUDA_FP16) // bug
testONNXModels("deconv_adjpad_2d", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, Deconvolution3D)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/frontend/frontend.cpp:592 Failed to compile layer "2":
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 2@weights Const data got different desc and content byte sizes (162 and 486 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] vpu/graph_transformer/src/frontend/frontend.cpp:439 Failed to compile layer "2":
// [ GENERAL_ERROR ] vpu/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 2@weights Const data got different desc and content byte sizes (162 and 486 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#endif
if (backend == DNN_BACKEND_OPENCV)
throw SkipTestException("OpenCV backend is not supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("deconv3d");
}
TEST_P(Test_ONNX_layers, Deconvolution3D_bias)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/frontend/frontend.cpp:592 Failed to compile layer "3":
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 3@weights Const data got different desc and content byte sizes (270 and 810 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] vpu/graph_transformer/src/frontend/frontend.cpp:439 Failed to compile layer "2":
// [ GENERAL_ERROR ] vpu/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 2@weights Const data got different desc and content byte sizes (162 and 486 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#endif
if (backend == DNN_BACKEND_OPENCV)
throw SkipTestException("OpenCV backend is not supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("deconv3d_bias");
}
TEST_P(Test_ONNX_layers, Deconvolution3D_pad)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/frontend/frontend.cpp:592 Failed to compile layer "3":
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 3@weights Const data got different desc and content byte sizes (108 and 432 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] vpu/graph_transformer/src/frontend/frontend.cpp:439 Failed to compile layer "2":
// [ GENERAL_ERROR ] vpu/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 2@weights Const data got different desc and content byte sizes (162 and 486 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#endif
if (backend == DNN_BACKEND_OPENCV)
throw SkipTestException("OpenCV backend is not supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("deconv3d_pad");
}
TEST_P(Test_ONNX_layers, Deconvolution3D_adjpad)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/frontend/frontend.cpp:592 Failed to compile layer "3":
// [ GENERAL_ERROR ] openvino/src/plugins/intel_myriad/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 3@weights Const data got different desc and content byte sizes (90 and 180 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// [ GENERAL_ERROR ] vpu/graph_transformer/src/frontend/frontend.cpp:439 Failed to compile layer "2":
// [ GENERAL_ERROR ] vpu/graph_transformer/src/model/model.cpp:198 duplicateData error: while duplicating 2@weights Const data got different desc and content byte sizes (162 and 486 respectively)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#endif
if (backend == DNN_BACKEND_OPENCV)
throw SkipTestException("OpenCV backend is not supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("deconv3d_adjpad");
}
TEST_P(Test_ONNX_layers, Dropout)
{
testONNXModels("dropout");
}
TEST_P(Test_ONNX_layers, Linear)
{
if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
testONNXModels("linear");
}
TEST_P(Test_ONNX_layers, ReLU)
{
testONNXModels("ReLU");
}
TEST_P(Test_ONNX_layers, PReLU)
{
testONNXModels("PReLU_slope");
}
TEST_P(Test_ONNX_layers, Clip)
{
testONNXModels("clip", npy);
}
TEST_P(Test_ONNX_layers, Clip_init)
{
testONNXModels("clip_init_min_max");
testONNXModels("clip_init_min");
testONNXModels("clip_init_max");
}
TEST_P(Test_ONNX_layers, Shape)
{
testONNXModels("shape_of_constant");
}
TEST_P(Test_ONNX_layers, ReduceMean)
{
testONNXModels("reduce_mean");
testONNXModels("reduce_mean_axis1");
testONNXModels("reduce_mean_axis2");
}
TEST_P(Test_ONNX_layers, ReduceSum)
{
testONNXModels("reduce_sum");
testONNXModels("reduce_sum_axis_dynamic_batch");
}
TEST_P(Test_ONNX_layers, ReduceMax)
{
testONNXModels("reduce_max");
}
TEST_P(Test_ONNX_layers, ReduceMax_axis_0)
{
testONNXModels("reduce_max_axis_0");
}
TEST_P(Test_ONNX_layers, ReduceMax_axis_1)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// [ GENERAL_ERROR ] AssertionFailed: !out.networkInputs.empty()
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("reduce_max_axis_1");
}
TEST_P(Test_ONNX_layers, Min)
{
testONNXModels("min", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, ArgLayer)
{
if (backend != DNN_BACKEND_OPENCV || target != DNN_TARGET_CPU)
throw SkipTestException("Only CPU is supported"); // FIXIT use tags
testONNXModels("argmax");
testONNXModels("argmin");
}
TEST_P(Test_ONNX_layers, Scale)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// accuracy (inf/nan)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// accuracy
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
// IE exception: mkldnn_node.cpp:238 Ngraph operation Reshape with name ReduceMean_0 has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// Ngraph operation Reshape with name ReduceMean_0 has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("scale");
}
TEST_P(Test_ONNX_layers, Scale_broadcast)
{
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA); // doesn't support broadcasting
testONNXModels("scale_broadcast", npy, 0, 0, false, true, 3);
}
TEST_P(Test_ONNX_layers, Scale_broadcast_mid)
{
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA); // doesn't support broadcasting
testONNXModels("scale_broadcast_mid", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, ReduceMean3D)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER); // Only CPU on DLIE backend is supported
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // Only CPU on DLIE backend is supported
#endif
if (backend == DNN_BACKEND_OPENCV && target != DNN_TARGET_CPU)
throw SkipTestException("Only CPU is supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("reduce_mean3d");
}
TEST_P(Test_ONNX_layers, MaxPooling_Sigmoid)
{
testONNXModels("maxpooling_sigmoid");
}
TEST_P(Test_ONNX_layers, Cast)
{
testONNXModels("cast");
}
TEST_P(Test_ONNX_layers, Power)
{
testONNXModels("pow2", npy, 0, 0, false, false);
}
4 years ago
TEST_P(Test_ONNX_layers, Exp)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("exp");
}
TEST_P(Test_ONNX_layers, Elementwise_Ceil)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("ceil");
}
TEST_P(Test_ONNX_layers, Elementwise_Floor)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("floor");
}
TEST_P(Test_ONNX_layers, Elementwise_Log)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("log");
}
TEST_P(Test_ONNX_layers, Elementwise_Round)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("round");
}
TEST_P(Test_ONNX_layers, Elementwise_Sqrt)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
testONNXModels("sqrt");
#endif
}
TEST_P(Test_ONNX_layers, Elementwise_not)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("not");
}
TEST_P(Test_ONNX_layers, Compare_EQ)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("equal");
}
TEST_P(Test_ONNX_layers, Compare_GT)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("greater");
}
TEST_P(Test_ONNX_layers, Greater_input_dtype_int64) {
testONNXModels("greater_input_dtype_int64");
}
TEST_P(Test_ONNX_layers, Compare_LT)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("less");
}
TEST_P(Test_ONNX_layers, Compare_GTorEQ)
{
testONNXModels("greater_or_equal");
}
TEST_P(Test_ONNX_layers, Compare_LEorEQ)
{
testONNXModels("less_or_equal");
}
TEST_P(Test_ONNX_layers, CompareSameDims_EQ)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("equal_same_dims", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, CompareSameDims_GT)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("greater_same_dims", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, CompareSameDims_LT)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: Function contains several inputs and outputs with one friendly name!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("less_same_dims", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Concatenation)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
testONNXModels("concatenation");
testONNXModels("concat_const_blobs");
}
TEST_P(Test_ONNX_layers, CumSumExclusiveInplace)
{
testONNXModels("cumsum_exclusive_inplace");
}
TEST_P(Test_ONNX_layers, Eltwise3D)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER); // Only CPU on DLIE backend is supported
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // Only CPU on DLIE backend is supported
#endif
testONNXModels("eltwise3d");
}
TEST_P(Test_ONNX_layers, AveragePooling)
{
testONNXModels("average_pooling");
}
TEST_P(Test_ONNX_layers, MaxPooling3D)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// accuracy
if (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16)
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: [ GENERAL_ERROR ] AssertionFailed: !expired()
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// accuracy
if (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16)
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
// IE exception: [ GENERAL_ERROR ] AssertionFailed: !expired()
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER); // Only CPU on DLIE backend is supported
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // Only CPU on DLIE backend is supported
#endif
if (backend == DNN_BACKEND_OPENCV && target != DNN_TARGET_CPU)
throw SkipTestException("Only CPU is supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("max_pool3d", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, AvePooling3D)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER); // Only CPU on DLIE backend is supported
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // Only CPU on DLIE backend is supported
#endif
if (backend == DNN_BACKEND_OPENCV && target != DNN_TARGET_CPU)
throw SkipTestException("Only CPU is supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
testONNXModels("ave_pool3d");
}
TEST_P(Test_ONNX_layers, PoolConv3D)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER); // Only CPU on DLIE backend is supported
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // Only CPU on DLIE backend is supported
#endif
if (backend == DNN_BACKEND_OPENCV && target != DNN_TARGET_CPU)
throw SkipTestException("Only CPU is supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
if (backend == DNN_BACKEND_CUDA && target == DNN_TARGET_CUDA_FP16)
{
// CUDA_FP16: cuDNN did not return a suitable algorithm for convolution.
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA_FP16);
}
testONNXModels("pool_conv_3d");
}
TEST_P(Test_ONNX_layers, BatchNormalization)
{
testONNXModels("batch_norm");
}
TEST_P(Test_ONNX_layers, BatchNormalization3D)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
testONNXModels("batch_norm_3d");
}
TEST_P(Test_ONNX_layers, BatchNormalizationUnfused)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021030000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // exception
#endif
testONNXModels("frozenBatchNorm2d");
}
TEST_P(Test_ONNX_layers, BatchNormalizationSubgraph)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021030000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // exception
#endif
testONNXModels("batch_norm_subgraph");
}
TEST_P(Test_ONNX_layers, NormalizeFusionSubgraph)
{
testONNXModels("normalize_fusion");
}
TEST_P(Test_ONNX_layers, Transpose)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
testONNXModels("transpose");
}
TEST_P(Test_ONNX_layers, Multiplication)
{
if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("mul");
}
TEST_P(Test_ONNX_layers, MatMul_2d)
{
testONNXModels("matmul_2d");
}
TEST_P(Test_ONNX_layers, MatMul_3d)
{
testONNXModels("matmul_3d");
}
TEST_P(Test_ONNX_layers, MatMul_4d)
{
testONNXModels("matmul_4d");
}
TEST_P(Test_ONNX_layers, MatMul_2d_init)
{
testONNXModels("matmul_2d_init");
}
TEST_P(Test_ONNX_layers, MatMul_3d_init)
{
testONNXModels("matmul_3d_init");
}
TEST_P(Test_ONNX_layers, MatMul_4d_init)
{
testONNXModels("matmul_4d_init");
}
TEST_P(Test_ONNX_layers, MatMul_init_2)
{
testONNXModels("matmul_init_2");
}
TEST_P(Test_ONNX_layers, MatMul_init_bcast)
{
testONNXModels("matmul_init_bcast");
}
TEST_P(Test_ONNX_layers, MatMulAdd)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// accuracy
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
#endif
if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
testONNXModels("matmul_add");
}
TEST_P(Test_ONNX_layers, Expand)
{
testONNXModels("expand");
}
TEST_P(Test_ONNX_layers, ExpandIdentity) {
testONNXModels("expand_identity");
}
TEST_P(Test_ONNX_layers, ExpandBatch) {
testONNXModels("expand_batch");
}
TEST_P(Test_ONNX_layers, ExpandChannels) {
testONNXModels("expand_channels");
}
TEST_P(Test_ONNX_layers, ExpandNegBatch) {
testONNXModels("expand_neg_batch");
}
TEST_P(Test_ONNX_layers, ExpandHW)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("expand_hw");
}
TEST_P(Test_ONNX_layers, Constant)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2018050000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD
&& getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("constant");
}
TEST_P(Test_ONNX_layers, Padding)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2019010000)
testONNXModels("padding", npy, 0, 0, false, false);
#else
testONNXModels("padding");
#endif
}
TEST_P(Test_ONNX_layers, Resize)
{
testONNXModels("resize_nearest");
testONNXModels("tf_half_pixel_for_nn");
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("resize_bilinear");
}
TEST_P(Test_ONNX_layers, ResizeUnfused)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("upsample_unfused_torch1.2");
testONNXModels("upsample_unfused_opset9_torch1.4");
testONNXModels("resize_nearest_unfused_opset11_torch1.4");
testONNXModels("resize_nearest_unfused_opset11_torch1.3");
testONNXModels("resize_bilinear_unfused_opset11_torch1.4");
}
TEST_P(Test_ONNX_layers, ResizeUnfusedTwoInputs)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2023000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("upsample_unfused_two_inputs_opset9_torch1.4", npy, 0, 0, false, true, 2);
testONNXModels("upsample_unfused_two_inputs_opset11_torch1.4", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, MultyInputs)
{
testONNXModels("multy_inputs", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Broadcast)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("channel_broadcast", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, DynamicResize)
{
testONNXModels("dynamic_resize_9", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_10", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_11", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_13", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_scale_9", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_scale_10", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_scale_11", npy, 0, 0, false, true, 2);
testONNXModels("dynamic_resize_scale_13", npy, 0, 0, false, true, 2);
testONNXModels("resize_size_opset11");
testONNXModels("resize_size_opset13");
}
TEST_P(Test_ONNX_layers, Resize_HumanSeg)
{
testONNXModels("resize_humanseg");
}
TEST_P(Test_ONNX_layers, Div)
{
const String model = _tf("models/div.onnx");
Net net = readNetFromONNX(model);
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
// Reference output values range is -68.80928, 2.991873. So to avoid computational
// difference for FP16 we'll perform reversed division (just swap inputs).
Mat inp1 = blobFromNPY(_tf("data/input_div_1.npy"));
Mat inp2 = blobFromNPY(_tf("data/input_div_0.npy"));
Mat ref = blobFromNPY(_tf("data/output_div.npy"));
cv::divide(1.0, ref, ref);
checkBackend(&inp1, &ref);
net.setInput(inp1, "0");
net.setInput(inp2, "1");
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
// NaryEltwise layer suuports only CPU for now
testONNXModels("div_test_1x1", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, DynamicReshape)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("dynamic_reshape");
testONNXModels("dynamic_reshape_opset_11");
testONNXModels("flatten_by_prod");
testONNXModels("flatten_const");
}
TEST_P(Test_ONNX_layers, Reshape)
{
testONNXModels("unsqueeze");
testONNXModels("unsqueeze_opset_13");
}
TEST_P(Test_ONNX_layers, Unsqueeze_Neg_Axes)
{
testONNXModels("unsqueeze_neg_axes");
}
TEST_P(Test_ONNX_layers, Squeeze)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
testONNXModels("squeeze");
testONNXModels("squeeze_axes_op13");
}
TEST_P(Test_ONNX_layers, ReduceL2)
{
testONNXModels("reduceL2");
testONNXModels("reduceL2_subgraph");
testONNXModels("reduceL2_subgraph_2");
testONNXModels("reduceL2_subgraph2_2");
}
TEST_P(Test_ONNX_layers, Split)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2023000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("split_0");
testONNXModels("split_1");
testONNXModels("split_2");
testONNXModels("split_3");
testONNXModels("split_4");
testONNXModels("split_5");
testONNXModels("split_6");
testONNXModels("split_neg_axis");
}
// Mul inside with 0-d tensor, output should be A x 1, but is 1 x A. PR #22652
TEST_P(Test_ONNX_layers, DISABLED_Split_sizes_0d)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
testONNXModels("split_sizes");
}
TEST_P(Test_ONNX_layers, Slice)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2019010000)
testONNXModels("slice", npy, 0, 0, false, false);
#else
testONNXModels("slice");
testONNXModels("slice_neg_starts");
testONNXModels("slice_opset_11");
testONNXModels("slice_neg_steps", pb);
#endif
}
TEST_P(Test_ONNX_layers, Slice_Steps_2DInput)
{
testONNXModels("slice_opset_11_steps_2d");
}
TEST_P(Test_ONNX_layers, Slice_Steps_3DInput)
{
testONNXModels("slice_opset_11_steps_3d");
}
TEST_P(Test_ONNX_layers, Slice_Steps_4DInput)
{
testONNXModels("slice_opset_11_steps_4d");
}
TEST_P(Test_ONNX_layers, Slice_Steps_5DInput)
{
testONNXModels("slice_opset_11_steps_5d");
}
TEST_P(Test_ONNX_layers, Slice_Nonseq_Axes)
{
testONNXModels("slice_nonseq_axes");
testONNXModels("slice_nonseq_axes_steps");
testONNXModels("slice_nonseq_miss_axes_steps");
}
TEST_P(Test_ONNX_layers, Slice_Neg_Axes)
{
testONNXModels("slice_neg_axes");
testONNXModels("slice_neg_axes_steps");
testONNXModels("slice_neg_miss_axes_steps");
}
TEST_P(Test_ONNX_layers, Softmax)
{
testONNXModels("softmax");
testONNXModels("log_softmax", npy, 0, 0, false, false);
testONNXModels("softmax_unfused");
}
TEST_P(Test_ONNX_layers, Split_EltwiseMax)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2023000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
testONNXModels("split_max");
}
TEST_P(Test_ONNX_layers, LSTM_Activations)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Node Block1326/lstm/reshape_0/permute was not assigned on any pointed device
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE Exception: Ngraph operation Reshape with name Block1237_Output_0_before_reshape has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
testONNXModels("lstm_cntk_tanh", pb, 0, 0, false, false);
}
// disabled due to poor handling of 1-d mats
TEST_P(Test_ONNX_layers, DISABLED_LSTM)
5 years ago
{
testONNXModels("lstm", npy, 0, 0, false, false);
5 years ago
}
// disabled due to poor handling of 1-d mats
TEST_P(Test_ONNX_layers, DISABLED_LSTM_bidirectional)
{
testONNXModels("lstm_bidirectional", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_hidden)
{
testONNXModels("hidden_lstm", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_hidden_bidirectional)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Node Transpose_45 was not assigned on any pointed device.
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
testONNXModels("hidden_lstm_bi", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, GRU)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Node GRU_22 was not assigned on any pointed device
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
testONNXModels("gru", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, gru_cell_batchsize_50_seqlen_1)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Node GRU_22 was not assigned on any pointed device
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("gru_cell_batchsize_50_seqlen_1", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, gru_cell_batchsize_5_seqlen_5)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Node GRU_22 was not assigned on any pointed device
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("gru_cell_batchsize_5_seqlen_5", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, gru_cell_batchsize_1_seqlen_50)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Node GRU_22 was not assigned on any pointed device
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("gru_cell_batchsize_1_seqlen_50", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, GRU_bidirectional)
{
testONNXModels("gru_bi", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_cell_forward)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// accuracy!
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// Ngraph operation Reshape with name LSTM_16/lstm_y/reshape has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("lstm_cell_forward", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_cell_bidirectional)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// Ngraph operation Reshape with name LSTM_16/lstm_y/reshape has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("lstm_cell_bidirectional", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_cell_with_peepholes)
{
testONNXModels("lstm_cell_with_peepholes", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_cell_batchsize_50_seqlen_1)
{
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lstm_cell_batchsize_50_seqlen_1", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_cell_batchsize_1_seqlen_50)
{
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lstm_cell_batchsize_1_seqlen_50", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_cell_batchsize_5_seqlen_5)
{
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lstm_cell_batchsize_5_seqlen_5", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, LSTM_init_h0_c0)
{
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lstm_init_h0_c0", npy, 0, 0, false, false, 3);
}
// epsilon is larger because onnx does not match with torch/opencv exactly
TEST_P(Test_ONNX_layers, LSTM_layout_seq)
{
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lstm_layout_0", npy, 0.005, 0.005, false, false, 3);
}
// epsilon is larger because onnx does not match with torch/opencv exactly
TEST_P(Test_ONNX_layers, LSTM_layout_batch)
{
if(backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lstm_layout_1", npy, 0.005, 0.005, false, false, 3);
}
Merge pull request #24037 from Abdurrahheem:ash/dev_einsum Add Support for Einsum Layer #24037 ### This PR adding support for [Einsum Layer](https://pytorch.org/docs/stable/generated/torch.einsum.html) (in progress). This PR is currently not to be merged but only reviewed. Test cases are located in [#1090](https://github.com/opencv/opencv_extra/pull/1090)RP in OpenCV extra **DONE**: - [x] 2-5D GMM support added - [x] Matrix transpose support added - [x] Reduction type comupte 'ij->j' - [x] 2nd shape computation - during forward **Next PRs**: - [ ] Broadcasting reduction "...ii ->...i" - [ ] Add lazy shape deduction. "...ij, ...jk->...ik" - [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik") - [ ] Add support for CUDA backend - [ ] BatchWiseMultiply optimize **Later in 5.x version (requires support for 1D matrices)**: - [ ] Add 1D vector multiplication support - [ ] Inter product "i, i" (problems with 1D shapes) ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
1 year ago
TEST_P(Test_ONNX_layers, DISABLED_Einsum_1D)
{
testONNXModels("einsum_1d", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, Einsum_2D)
{
testONNXModels("einsum_2d", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, Einsum_2D_Ellipses)
{
testONNXModels("einsum_2d_ellipses", npy, 0, 0, false, false, 2);
}
Merge pull request #24037 from Abdurrahheem:ash/dev_einsum Add Support for Einsum Layer #24037 ### This PR adding support for [Einsum Layer](https://pytorch.org/docs/stable/generated/torch.einsum.html) (in progress). This PR is currently not to be merged but only reviewed. Test cases are located in [#1090](https://github.com/opencv/opencv_extra/pull/1090)RP in OpenCV extra **DONE**: - [x] 2-5D GMM support added - [x] Matrix transpose support added - [x] Reduction type comupte 'ij->j' - [x] 2nd shape computation - during forward **Next PRs**: - [ ] Broadcasting reduction "...ii ->...i" - [ ] Add lazy shape deduction. "...ij, ...jk->...ik" - [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik") - [ ] Add support for CUDA backend - [ ] BatchWiseMultiply optimize **Later in 5.x version (requires support for 1D matrices)**: - [ ] Add 1D vector multiplication support - [ ] Inter product "i, i" (problems with 1D shapes) ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
1 year ago
TEST_P(Test_ONNX_layers, Einsum_3D)
{
testONNXModels("einsum_3d", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, Einsum_4D)
{
testONNXModels("einsum_4d", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, Einsum_5D)
{
testONNXModels("einsum_5d", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, DISABLED_Einsum_InnerProduct)
{
testONNXModels("einsum_inner", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, DISABLED_Einsum_HadamardProduct)
{
testONNXModels("einsum_hadamard", npy, 0, 0, false, false, 2);
}
TEST_P(Test_ONNX_layers, Einsum_Batch_Diagonal)
Merge pull request #24037 from Abdurrahheem:ash/dev_einsum Add Support for Einsum Layer #24037 ### This PR adding support for [Einsum Layer](https://pytorch.org/docs/stable/generated/torch.einsum.html) (in progress). This PR is currently not to be merged but only reviewed. Test cases are located in [#1090](https://github.com/opencv/opencv_extra/pull/1090)RP in OpenCV extra **DONE**: - [x] 2-5D GMM support added - [x] Matrix transpose support added - [x] Reduction type comupte 'ij->j' - [x] 2nd shape computation - during forward **Next PRs**: - [ ] Broadcasting reduction "...ii ->...i" - [ ] Add lazy shape deduction. "...ij, ...jk->...ik" - [ ] Add implicit output computation support. "bij,bjk ->" (output subscripts should be "bik") - [ ] Add support for CUDA backend - [ ] BatchWiseMultiply optimize **Later in 5.x version (requires support for 1D matrices)**: - [ ] Add 1D vector multiplication support - [ ] Inter product "i, i" (problems with 1D shapes) ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
1 year ago
{
testONNXModels("einsum_batch_diagonal", npy, 0, 0, false, false, 1);
}
TEST_P(Test_ONNX_layers, Einsum_Sum)
{
testONNXModels("einsum_sum", npy, 0, 0, false, false, 1);
}
TEST_P(Test_ONNX_layers, Einsum_transpose)
{
testONNXModels("einsum_transpose", npy, 0, 0, false, false, 1);
}
TEST_P(Test_ONNX_layers, Pad2d_Unfused)
{
testONNXModels("ReflectionPad2d");
testONNXModels("ZeroPad2d");
}
TEST_P(Test_ONNX_layers, LinearWithConstant)
{
if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2020040000)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE);
#endif
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA);
testONNXModels("lin_with_constant");
}
TEST_P(Test_ONNX_layers, MatmulWithTwoInputs)
{
if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2020040000)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE);
#endif
testONNXModels("matmul_with_two_inputs");
}
TEST_P(Test_ONNX_layers, ResizeOpset11_Torch1_6)
{
testONNXModels("resize_opset11_torch1.6");
}
TEST_P(Test_ONNX_layers, Mish)
{
testONNXModels("mish");
testONNXModels("mish_no_softplus");
}
TEST_P(Test_ONNX_layers, CalculatePads)
{
testONNXModels("calc_pads");
}
TEST_P(Test_ONNX_layers, Conv1d)
{
testONNXModels("conv1d");
}
TEST_P(Test_ONNX_layers, Conv1d_bias)
{
testONNXModels("conv1d_bias");
}
TEST_P(Test_ONNX_layers, Conv1d_variable_weight)
{
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA); // not supported
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN); // not supported
String basename = "conv1d_variable_w";
Net net = readNetFromONNX(_tf("models/" + basename + ".onnx"));
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
Mat input = blobFromNPY(_tf("data/input_" + basename + "_0.npy"));
Mat weights = blobFromNPY(_tf("data/input_" + basename + "_1.npy"));
Mat ref = blobFromNPY(_tf("data/output_" + basename + ".npy"));
net.setInput(input, "0");
net.setInput(weights, "1");
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
}
TEST_P(Test_ONNX_layers, Conv1d_variable_weight_bias)
{
if (backend == DNN_BACKEND_CUDA)
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA); // not supported
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN); // not supported
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
if (target == DNN_TARGET_CPU && getInferenceEngineCPUType() == CV_DNN_INFERENCE_ENGINE_CPU_TYPE_ARM_COMPUTE)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_ARM_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
String basename = "conv1d_variable_wb";
Net net = readNetFromONNX(_tf("models/" + basename + ".onnx"));
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
Mat input = blobFromNPY(_tf("data/input_" + basename + "_0.npy"));
Mat weights = blobFromNPY(_tf("data/input_" + basename + "_1.npy"));
Mat bias = blobFromNPY(_tf("data/input_" + basename + "_2.npy"));
Mat ref = blobFromNPY(_tf("data/output_" + basename + ".npy"));
net.setInput(input, "0");
net.setInput(weights, "1");
net.setInput(bias, "bias");
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
}
TEST_P(Test_ONNX_layers, GatherMultiOutput)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE Exception: Ngraph operation Reshape with name 6 has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021030000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // exception
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // exception
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LE(2021030000)
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE);
#endif
testONNXModels("gather_multi_output", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, DynamicAxes_squeeze_and_conv)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("squeeze_and_conv_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_unsqueeze_and_conv)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("unsqueeze_and_conv_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_gather)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("gather_dynamic_axes", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, DynamicAxes_gather_scalar)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// accuracy
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// accuracy
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#elif defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("gather_scalar_dynamic_axes", npy, 0, 0, false, false);
}
TEST_P(Test_ONNX_layers, DynamicAxes_slice)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("slice_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_slice_opset_11)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("slice_opset_11_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_resize_opset11_torch16)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("resize_opset11_torch1.6_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_average_pooling)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("average_pooling_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_maxpooling_sigmoid)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("maxpooling_sigmoid_dynamic_axes");
}
TEST_P(Test_ONNX_layers, DynamicAxes_dynamic_batch)
{
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#if INF_ENGINE_VER_MAJOR_LT(2021000000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#endif
testONNXModels("dynamic_batch");
}
TEST_P(Test_ONNX_layers, MaxPool1d)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_GE(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
{
// 2021.4: [ GENERAL_ERROR ] AssertionFailed: !expired()
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
testONNXModels("maxpooling_1d");
}
TEST_P(Test_ONNX_layers, MaxPoolSigmoid1d)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_CPU, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
testONNXModels("maxpooling_sigmoid_1d");
}
TEST_P(Test_ONNX_layers, MaxPool1d_Twise)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
testONNXModels("two_maxpooling_1d");
}
TEST_P(Test_ONNX_layers, AvePool1d)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
testONNXModels("average_pooling_1d");
}
TEST_P(Test_ONNX_layers, PoolConv1d)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
#endif
testONNXModels("pool_conv_1d");
}
TEST_P(Test_ONNX_layers, ConvResizePool1d)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// IE Exception: Ngraph operation Reshape with name 15 has dynamic output shape on 0 port, but CPU plug-in supports only static shape
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#endif
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#if INF_ENGINE_VER_MAJOR_EQ(2021030000)
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // exception
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // exception
#endif
}
#endif
const double lInf = (target == DNN_TARGET_CPU_FP16) ? 0.024 : default_lInf;
testONNXModels("conv_resize_pool_1d", npy, default_l1, lInf);
}
TEST_P(Test_ONNX_layers, DepthWiseAdd)
{
testONNXModels("depthwiseconv_add");
}
TEST_P(Test_ONNX_layers, DepthStride2)
{
testONNXModels("depthwise_stride2");
}
TEST_P(Test_ONNX_layers, SubFromConst)
{
testONNXModels("sub_from_const1");
testONNXModels("sub_from_const_eltwise");
testONNXModels("sub_from_const_broadcast");
}
TEST_P(Test_ONNX_layers, DivConst)
{
testONNXModels("div_const");
}
TEST_P(Test_ONNX_layers, Gemm)
{
testONNXModels("gemm_no_transB");
testONNXModels("gemm_transB_0");
testONNXModels("gemm_first_const");
}
TEST_P(Test_ONNX_layers, Gemm_bias)
{
testONNXModels("gemm_vector_bias");
}
TEST_P(Test_ONNX_layers, Quantized_Convolution)
{
// The difference of QOperator and QDQ format:
// https://onnxruntime.ai/docs/performance/quantization.html#onnx-quantization-representation-format.
{
SCOPED_TRACE("QOperator quantized model.");
testONNXModels("quantized_conv_uint8_weights", npy, 0.004, 0.02);
testONNXModels("quantized_conv_int8_weights", npy, 0.03, 0.5);
testONNXModels("quantized_conv_per_channel_weights", npy, 0.06, 0.4);
testONNXModels("quantized_conv_asymmetric_pads_int8_weights");
}
{
SCOPED_TRACE("QDQ quantized model.");
testONNXModels("quantized_conv_uint8_weights_qdq", npy, 0.004, 0.02);
testONNXModels("quantized_conv_int8_weights_qdq", npy, 0.03, 0.5);
testONNXModels("quantized_conv_per_channel_weights_qdq", npy, 0.06, 0.4);
}
}
TEST_P(Test_ONNX_layers, Quantized_MatMul)
{
testONNXModels("quantized_matmul_uint8_weights", npy, 0.005, 0.007);
testONNXModels("quantized_matmul_int8_weights", npy, 0.06, 0.2);
testONNXModels("quantized_matmul_per_channel_weights", npy, 0.06, 0.22);
}
TEST_P(Test_ONNX_layers, Quantized_Gemm)
{
testONNXModels("quantized_gemm", npy);
}
TEST_P(Test_ONNX_layers, Quantized_MatMul_Variable_Weights)
{
// Unsupported
EXPECT_THROW(
{
testONNXModels("quantized_matmul_variable_inputs");
}, cv::Exception);
}
TEST_P(Test_ONNX_layers, Quantized_Eltwise)
{
testONNXModels("quantized_eltwise");
}
TEST_P(Test_ONNX_layers, Quantized_Eltwise_Scalar)
{
testONNXModels("quantized_eltwise_scalar");
}
TEST_P(Test_ONNX_layers, Quantized_Eltwise_Broadcast)
{
testONNXModels("quantized_eltwise_broadcast");
}
TEST_P(Test_ONNX_layers, Quantized_LeakyReLU)
{
testONNXModels("quantized_leaky_relu");
}
TEST_P(Test_ONNX_layers, Quantized_Sigmoid)
{
testONNXModels("quantized_sigmoid");
}
TEST_P(Test_ONNX_layers, Quantized_MaxPool)
{
testONNXModels("quantized_maxpool");
}
TEST_P(Test_ONNX_layers, Quantized_AvgPool)
{
testONNXModels("quantized_avgpool");
}
TEST_P(Test_ONNX_layers, Quantized_Split)
{
testONNXModels("quantized_split");
}
TEST_P(Test_ONNX_layers, Quantized_Pad)
{
testONNXModels("quantized_padding");
}
TEST_P(Test_ONNX_layers, Quantized_Reshape)
{
testONNXModels("quantized_reshape");
}
TEST_P(Test_ONNX_layers, Quantized_Transpose)
{
testONNXModels("quantized_transpose");
}
TEST_P(Test_ONNX_layers, Quantized_Squeeze)
{
testONNXModels("quantized_squeeze");
}
TEST_P(Test_ONNX_layers, Quantized_Unsqueeze)
{
testONNXModels("quantized_unsqueeze");
}
TEST_P(Test_ONNX_layers, Quantized_Resize)
{
testONNXModels("quantized_resize_nearest");
Merge pull request #23987 from dkurt:openvino_int8_backend OpenVINO backend for INT8 models #23987 ### Pull Request Readiness Checklist TODO: - [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069) - [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum) - [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039) - [x] Single layer tests (convolution) - [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~ Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`: | backend | performance (median time) | |---|---| | OpenCV | 77.42ms | | OpenVINO 2023.0 | 10.90ms | CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz` Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef --- See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
1 year ago
double l1 = backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH ? 0.0013 : 2e-4;
testONNXModels("quantized_resize_bilinear", npy, l1, 0.003);
l1 = backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH ? 0.0013 : 3e-4;
testONNXModels("quantized_resize_bilinear_align", npy, l1, 0.003);
}
TEST_P(Test_ONNX_layers, Quantized_Concat)
{
Merge pull request #23987 from dkurt:openvino_int8_backend OpenVINO backend for INT8 models #23987 ### Pull Request Readiness Checklist TODO: - [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069) - [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum) - [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039) - [x] Single layer tests (convolution) - [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~ Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`: | backend | performance (median time) | |---|---| | OpenCV | 77.42ms | | OpenVINO 2023.0 | 10.90ms | CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz` Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef --- See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
1 year ago
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
testONNXModels("quantized_concat");
testONNXModels("quantized_concat_const_blob");
}
TEST_P(Test_ONNX_layers, Quantized_Constant)
{
testONNXModels("quantized_constant", npy, 0.002, 0.008);
}
TEST_P(Test_ONNX_layers, OutputRegistration)
{
testONNXModels("output_registration", npy, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, QLinearSoftmax)
{
Merge pull request #23987 from dkurt:openvino_int8_backend OpenVINO backend for INT8 models #23987 ### Pull Request Readiness Checklist TODO: - [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069) - [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum) - [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039) - [x] Single layer tests (convolution) - [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~ Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`: | backend | performance (median time) | |---|---| | OpenCV | 77.42ms | | OpenVINO 2023.0 | 10.90ms | CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz` Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef --- See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
1 year ago
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
testONNXModels("qlinearsoftmax_v11", npy, 0.002, 0.002); // 2D coerced
testONNXModels("qlinearsoftmax_v13", npy, 0.002, 0.002);
}
INSTANTIATE_TEST_CASE_P(/*nothing*/, Test_ONNX_layers, dnnBackendsAndTargets());
class Test_ONNX_nets : public Test_ONNX_layers
{
public:
Test_ONNX_nets() { required = false; }
};
TEST_P(Test_ONNX_nets, Alexnet)
{
#if defined(OPENCV_32BIT_CONFIGURATION) && (defined(HAVE_OPENCL) || defined(_WIN32))
applyTestTag(CV_TEST_TAG_MEMORY_2GB);
#else
applyTestTag(target == DNN_TARGET_CPU ? CV_TEST_TAG_MEMORY_512MB : CV_TEST_TAG_MEMORY_1GB);
#endif
const String model = _tf("models/alexnet.onnx", false);
Net net = readNetFromONNX(model);
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
net.enableWinograd(false);
Mat inp = imread(_tf("../grace_hopper_227.png"));
Mat ref = blobFromNPY(_tf("../caffe_alexnet_prob.npy"));
checkBackend(&inp, &ref);
net.setInput(blobFromImage(inp, 1.0f, Size(227, 227), Scalar(), false));
ASSERT_FALSE(net.empty());
Mat out = net.forward();
normAssert(out, ref, "", default_l1, default_lInf);
expectNoFallbacksFromIE(net);
}
TEST_P(Test_ONNX_nets, RAFT)
{
applyTestTag(CV_TEST_TAG_LONG, CV_TEST_TAG_DEBUG_VERYLONG, CV_TEST_TAG_MEMORY_2GB);
std::string weight_path = _tf("models/optical_flow_estimation_raft_2023aug.onnx", false);
std::string img0_path = findDataFile(std::string("gpu/opticalflow/frame0.png"));
std::string img1_path = findDataFile(std::string("gpu/opticalflow/frame1.png"));
Size target_size{480, 360};
auto img0 = imread(img0_path);
auto img1 = imread(img1_path);
auto blob0 = blobFromImage(img0, 1.0, target_size, 0, true);
auto blob1 = blobFromImage(img1, 1.0, target_size, 0, true);
auto net = readNet(weight_path);
net.setInput(blob0, "0");
net.setInput(blob1, "1");
std::vector<std::string> outnames{"12007", "12006"};
std::vector<Mat> outs;
net.forward(outs, outnames);
// output 12006 is not checked to save space in opencv_extra since its ref is > 1MB,
// and output 12006 is calculated from 12007 so checking 12007 is sufficient.
std::string ref_12700_path = _tf("data/output_optical_flow_estimation_raft_2023aug.npy");
auto ref0 = blobFromNPY(ref_12700_path);
normAssert(ref0, outs[0], "", 1e-5, 1.8e-4);
}
TEST_P(Test_ONNX_nets, Squeezenet)
{
testONNXModels("squeezenet", pb);
}
TEST_P(Test_ONNX_nets, Googlenet)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// accuracy
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
// accuracy
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
const String model = _tf("models/googlenet.onnx", false);
Net net = readNetFromONNX(model);
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
if (target == DNN_TARGET_CPU_FP16)
net.enableWinograd(false);
std::vector<Mat> images;
images.push_back( imread(_tf("../googlenet_0.png")) );
images.push_back( imread(_tf("../googlenet_1.png")) );
Mat inp = blobFromImages(images, 1.0f, Size(), Scalar(), false);
Mat ref = blobFromNPY(_tf("../googlenet_prob.npy"));
checkBackend(&inp, &ref);
net.setInput(inp);
ASSERT_FALSE(net.empty());
Mat out = net.forward();
normAssert(ref, out, "", default_l1, default_lInf);
expectNoFallbacksFromIE(net);
}
TEST_P(Test_ONNX_nets, CaffeNet)
{
#if defined(OPENCV_32BIT_CONFIGURATION) && (defined(HAVE_OPENCL) || defined(_WIN32))
applyTestTag(CV_TEST_TAG_MEMORY_2GB);
#else
applyTestTag(target == DNN_TARGET_CPU ? CV_TEST_TAG_MEMORY_512MB : CV_TEST_TAG_MEMORY_1GB);
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2019030000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD
&& getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
testONNXModels("caffenet", pb);
}
TEST_P(Test_ONNX_nets, RCNN_ILSVRC13)
{
#if defined(OPENCV_32BIT_CONFIGURATION) && (defined(HAVE_OPENCL) || defined(_WIN32))
applyTestTag(CV_TEST_TAG_MEMORY_2GB);
#else
applyTestTag(target == DNN_TARGET_CPU ? CV_TEST_TAG_MEMORY_512MB : CV_TEST_TAG_MEMORY_1GB);
#endif
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2019030000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD
&& getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
// Reference output values are in range [-4.992, -1.161]
testONNXModels("rcnn_ilsvrc13", pb, 0.0046);
}
TEST_P(Test_ONNX_nets, VGG16_bn)
{
applyTestTag(CV_TEST_TAG_MEMORY_6GB); // > 2.3Gb
// output range: [-16; 27], after Softmax [0; 0.67]
const double lInf = (target == DNN_TARGET_MYRIAD) ? 0.038 : default_lInf;
testONNXModels("vgg16-bn", pb, default_l1, lInf, true);
}
TEST_P(Test_ONNX_nets, ZFNet)
{
applyTestTag(CV_TEST_TAG_MEMORY_2GB);
testONNXModels("zfnet512", pb);
}
TEST_P(Test_ONNX_nets, ResNet18v1)
{
applyTestTag(CV_TEST_TAG_MEMORY_512MB);
// output range: [-16; 22], after Softmax [0, 0.51]
testONNXModels("resnet18v1", pb, default_l1, default_lInf, true, target != DNN_TARGET_MYRIAD);
}
TEST_P(Test_ONNX_nets, ResNet50v1)
{
applyTestTag(CV_TEST_TAG_MEMORY_512MB);
// output range: [-67; 75], after Softmax [0, 0.98]
testONNXModels("resnet50v1", pb, default_l1, default_lInf, true, target != DNN_TARGET_MYRIAD);
}
TEST_P(Test_ONNX_nets, ResNet50_Int8)
{
testONNXModels("resnet50_int8", pb, default_l1, default_lInf, true);
}
TEST_P(Test_ONNX_nets, ResNet101_DUC_HDC)
{
applyTestTag(CV_TEST_TAG_VERYLONG);
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_GE(2019010000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
#endif
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
#endif
if (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_OPENCL)
{
if (backend == DNN_BACKEND_OPENCV)
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_OPENCL : CV_TEST_TAG_DNN_SKIP_OPENCL_FP16);
throw SkipTestException("Test is disabled for OpenCL targets");
}
testONNXModels("resnet101_duc_hdc", pb);
}
TEST_P(Test_ONNX_nets, TinyYolov2)
{
applyTestTag(CV_TEST_TAG_MEMORY_512MB);
if (cvtest::skipUnstableTests)
throw SkipTestException("Skip unstable test");
#if defined(INF_ENGINE_RELEASE)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019
&& (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16)
)
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_MYRIAD && getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X
)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X,
backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 ?
CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER :
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
// output range: [-11; 8]
double l1 = default_l1, lInf = default_lInf;
Merge pull request #22275 from zihaomu:fp16_support_conv DNN: FP16 support on Convolution 2D #22275 ## FP16 support on ARM platform This PR proposes to support FP16 backend in Convolution. For now, we only support FP16 at ARM aarch64. In addition to adding fp16, I also added `seperateIm2col` optimization in this patch. ## How to use FP16 to speed up convolution? ``` Net net = readNet(modelPath); net.setPreferableTarget(DNN_TARGET_CPU_FP16); net.setInput(blob); Mat output = net.forward(); ``` ### TODO List | Task | Status | Remarks | |:-------:|:--------:|:------------:| | Convolution 2D FP16 | :heavy_check_mark: | Done | | Winograd FP16 | Because the current modification has reached 2k lines, winograd fp16 will be completed in the next PR. | | | Accuracy Test | :heavy_check_mark: | Done | | Performance Test | :heavy_check_mark: | Done | | Compiler bug | :heavy_check_mark: | Done | ### Speed Test for FP 16. **Test on M1 chip, 4 threads.** | Model Name | FP32 (Conv+Wino) | Conv(FP16) + Wino(FP 32) | |:-------:|:--------:|:------------:| | ReseNet 50 | 26.0 ms | **18.05 ms** (25% speed up)| | MobileNet V2 | 4.17 ms | **3.09 ms (29% speed up)** | ### Speed Test for `seperateIm2col` trick on X86. **Test on AMD 5600x, 12 threads.** | Model Name | 4.x | Patch | |:-------:|:--------:|:------------:| | MobileNet V2 | 5.6 ms | **3.0 ms (46% speed up)** | ### Performance Test #### Performance Test of X86 platform: AMD 5600X, with `-perf_threas=1` |Name of Test|4.x|patch|patch vs 4.x (x-factor)| |---|:-:|:-:|:-:| |Name of Test|4.x 0|fp16pr final|fp16pr final vs 4.x 0 (x-factor)| |---|:-:|:-:|:-:| |conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 19}, OCN=2, G=2, S=2, P=(1, 1), BIAS, OCV/CPU)|0.001|0.001|1.00| |conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 25}, OCN=2, G=2, P=(2, 2), PM=SAME, OCV/CPU)|0.001|0.001|1.03| |conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 6, 10}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.001|0.001|0.92| |conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.002|0.003|0.95| |conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.006|0.006|1.00| |conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.045|0.033|1.39| |conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)|0.011|0.009|1.17| |conv3d::Conv3D::(GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)|0.109|0.078|1.39| |conv3d::Conv3D::(GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)|0.040|0.042|0.94| |conv3d::Conv3D::(GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.326|0.342|0.95| |conv3d::Conv3D::(GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.580|0.589|0.99| |conv3d::Conv3D::(GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)|1.293|1.382|0.94| |conv3d::Conv3D::(GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)|3.590|3.710|0.97| |conv3d::Conv3D::(GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)|1.120|1.191|0.94| |conv3d::Conv3D::(GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)|2.576|2.872|0.90| |conv3d::Conv3D::(GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)|4.599|4.670|0.98| |conv3d::Conv3D::(GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)|9.230|9.582|0.96| |conv3d::Conv3D::(GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)|65.946|69.381|0.95| |conv3d::Conv3D::(GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)|18.915|19.289|0.98| |conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU)|1.404|1.457|0.96| |conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU)|2.060|1.501|1.37| |conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU)|1.409|1.464|0.96| |conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)|1.793|1.838|0.98| |conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)|1.207|1.199|1.01| |conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)|1.277|1.275|1.00| |conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|2.319|2.370|0.98| |conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU)|1.351|1.346|1.00| |conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU)|3.520|3.612|0.97| |conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.876|1.880|1.00| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU)|1.981|1.995|0.99| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU)|2.620|2.627|1.00| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU)|4.202|4.123|1.02| |conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|2.429|2.445|0.99| |conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|2.591|2.576|1.01| |conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)|3.005|2.998|1.00| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU)|3.515|3.532|1.00| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU)|3.115|3.134|0.99| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|3.937|3.899|1.01| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU)|5.533|5.471|1.01| |conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|3.472|3.464|1.00| |conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)|4.302|4.322|1.00| |conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)|6.100|6.035|1.01| |conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)|6.580|6.484|1.01| |conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|9.741|9.634|1.01| |conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|10.131|10.156|1.00| |conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|12.391|12.350|1.00| |conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU)|91.074|87.893|1.04| |conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|5.903|5.903|1.00| |conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU)|6.890|6.794|1.01| |conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)|5.160|5.131|1.01| |conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|4.970|5.036|0.99| |conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|5.045|5.015|1.01| |conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)|11.583|11.343|1.02| |conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)|5.348|5.320|1.01| |conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU)|5.357|5.396|0.99| |conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU)|6.050|6.006|1.01| |conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU)|5.952|5.953|1.00| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU)|8.014|8.014|1.00| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU)|12.472|12.577|0.99| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU)|10.803|10.655|1.01| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU)|18.429|13.405|1.37| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU)|6.659|6.647|1.00| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU)|14.192|13.819|1.03| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU)|6.045|6.068|1.00| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)|12.742|12.828|0.99| |conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU)|8.046|7.773|1.04| |conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.440|17.192|1.01| |conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)|15.418|14.972|1.03| |conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)|0.430|0.430|1.00| |conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)|6.692|6.663|1.00| |conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU)|6.350|6.347|1.00| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)|0.267|0.265|1.01| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)|7.755|7.558|1.03| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)|0.203|0.202|1.00| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|10.663|10.576|1.01| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)|10.827|10.614|1.02| |conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU)|7.049|6.947|1.01| |conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU)|6.900|6.901|1.00| |conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)|0.165|0.165|1.00| |conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)|17.953|17.251|1.04| |conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU)|7.430|7.320|1.01| |conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU)|22.187|21.705|1.02| |conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU)|8.349|8.126|1.03| |conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)|8.273|8.297|1.00| |conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU)|8.169|8.094|1.01| |conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)|13.602|13.359|1.02| |conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU)|8.633|8.584|1.01| |conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)|29.339|28.897|1.02| |conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|13.000|12.920|1.01| |conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|14.262|13.319|1.07| |conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|27.453|27.253|1.01| |conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU)|32.052|27.269|1.18| |conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|15.363|15.208|1.01| |conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|18.543|18.434|1.01| |conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)|39.114|37.954|1.03| |conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|36.271|36.972|0.98| |conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|19.262|19.427|0.99| |conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|19.298|19.349|1.00| |conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|20.261|19.847|1.02| |conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|21.867|21.525|1.02| |conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU)|51.756|49.979|1.04| |conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|28.133|27.060|1.04| |conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU)|25.035|24.980|1.00| |conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|25.858|25.821|1.00| |conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|27.313|27.149|1.01| |conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)|28.219|28.111|1.00| |conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|46.025|46.674|0.99| |conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|30.220|29.446|1.03| |conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|49.410|48.708|1.01| |conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|38.203|38.001|1.01| |conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|39.961|39.021|1.02| |conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|48.685|47.075|1.03| |conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|75.114|72.586|1.03| |conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)|41.222|41.144|1.00| |conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU)|46.220|46.353|1.00| |conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU)|98.201|98.771|0.99| |conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|100.106|96.971|1.03| |conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|146.977|140.445|1.05| |conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU)|198.618|194.665|1.02| #### Performance Test of ARM platform: apple M1, with `-perf_threas=1` Min (ms) |Name of Test|4.x|patch|4.x vs patch (x-factor)| |---|:-:|:-:|:-:| |conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 19}, OCN=2, G=2, S=2, P=(1, 1), BIAS, OCV/CPU)|0.001|0.001|1.07| |conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 2, 25}, OCN=2, G=2, P=(2, 2), PM=SAME, OCV/CPU)|0.001|0.001|1.10| |conv1d::Conv1D::(GFLOPS=0.000, K=[3], IN={1, 6, 10}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.002|0.002|0.97| |conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 4, 9, 10, 10}, OCN=4, S=[1 x 1 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.003|0.003|0.84| |conv3d::Conv3D::(GFLOPS=0.000, K=[1 x 1 x 1], IN={1, 8, 1, 10, 10}, OCN=8, G=8, P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.009|0.009|1.00| |conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 3 x 3], IN={1, 2, 19, 19, 19}, OCN=2, G=2, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), BIAS, OCV/CPU)|0.027|0.030|0.90| |conv3d::Conv3D::(GFLOPS=0.000, K=[3 x 4 x 2], IN={1, 4, 8, 10, 10}, OCN=4, G=4, S=[1 x 2 x 1], BIAS, OCV/CPU)|0.008|0.007|1.07| |conv3d::Conv3D::(GFLOPS=0.001, K=[3 x 3 x 3], IN={1, 2, 25, 19, 19}, OCN=2, G=2, S=[1 x 2 x 2], P=(2, 2) x (2, 2) x (2, 2), PM=SAME, OCV/CPU)|0.066|0.072|0.91| |conv3d::Conv3D::(GFLOPS=0.002, K=[3 x 1 x 4], IN={1, 14, 5, 10, 10}, OCN=14, PM=SAME, OCV/CPU)|0.090|0.054|1.68| |conv3d::Conv3D::(GFLOPS=0.006, K=[5 x 5 x 5], IN={1, 4, 50, 19, 19}, OCN=4, S=[2 x 2 x 2], P=(1, 1) x (1, 1) x (1, 1), PM=VALID, OCV/CPU)|0.328|0.409|0.80| |conv3d::Conv3D::(GFLOPS=0.027, K=[3 x 3 x 3], IN={1, 6, 10, 38, 50}, OCN=6, PM=VALID, BIAS, OCV/CPU)|0.659|0.697|0.95| |conv3d::Conv3D::(GFLOPS=0.030, K=[5 x 5 x 5], IN={1, 6, 19, 19, 19}, OCN=6, G=2, OCV/CPU)|1.266|1.403|0.90| |conv3d::Conv3D::(GFLOPS=0.045, K=[7 x 7 x 7], IN={1, 2, 38, 38, 38}, OCN=2, S=[1 x 2 x 1], OCV/CPU)|3.550|4.145|0.86| |conv3d::Conv3D::(GFLOPS=0.053, K=[3 x 3 x 3], IN={1, 10, 98, 10, 10}, OCN=10, PM=SAME, OCV/CPU)|1.188|1.375|0.86| |conv3d::Conv3D::(GFLOPS=0.071, K=[7 x 7 x 7], IN={1, 6, 15, 19, 19}, OCN=6, S=[2 x 1 x 1], P=(3, 3) x (3, 3) x (3, 3), PM=SAME, BIAS, OCV/CPU)|2.683|3.236|0.83| |conv3d::Conv3D::(GFLOPS=0.093, K=[5 x 5 x 5], IN={1, 4, 40, 75, 75}, OCN=4, S=[2 x 2 x 2], OCV/CPU)|4.491|5.501|0.82| |conv3d::Conv3D::(GFLOPS=0.116, K=[5 x 5 x 5], IN={1, 2, 21, 75, 100}, OCN=2, BIAS, OCV/CPU)|8.916|10.181|0.88| |conv3d::Conv3D::(GFLOPS=1.267, K=[5 x 5 x 5], IN={1, 3, 75, 75, 100}, OCN=3, PM=SAME, BIAS, OCV/CPU)|69.995|72.296|0.97| |conv3d::Conv3D::(GFLOPS=1.343, K=[3 x 3 x 3], IN={1, 11, 9, 150, 200}, OCN=11, PM=VALID, BIAS, OCV/CPU)|22.531|23.139|0.97| |conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU)|2.239|1.933|1.16| |conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 512, 26, 26}, OCN=256, OCV/CPU_FP16)|-|1.010|-| |conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU)|3.134|2.068|1.52| |conv::Conv::(GFLOPS=0.177, K=[1 x 1], IN={1, 1024, 13, 13}, OCN=512, OCV/CPU_FP16)|-|1.062|-| |conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU)|1.918|1.920|1.00| |conv::Conv::(GFLOPS=0.178, K=[1 x 1], IN={1, 256, 52, 52}, OCN=128, OCV/CPU_FP16)|-|1.014|-| |conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU)|2.340|2.352|0.99| |conv::Conv::(GFLOPS=0.210, K=[1 x 1], IN={1, 576, 38, 50}, OCN=96, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.247|-| |conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU)|1.116|1.111|1.00| |conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 128, 56, 56}, OCN=32, P=[1 x 1], OCV/CPU_FP16)|-|1.114|-| |conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU)|1.116|1.112|1.00| |conv::Conv::(GFLOPS=0.231, K=[3 x 3], IN={1, 256, 14, 14}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|1.113|-| |conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|3.067|3.085|0.99| |conv::Conv::(GFLOPS=0.280, K=[1 x 1], IN={1, 576, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.622|-| |conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU)|1.153|1.187|0.97| |conv::Conv::(GFLOPS=0.302, K=[3 x 3], IN={1, 64, 64, 64}, OCN=64, PM=SAME, OCV/CPU_FP16)|-|1.150|-| |conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU)|4.804|4.849|0.99| |conv::Conv::(GFLOPS=0.357, K=[1 x 1], IN={1, 64, 208, 208}, OCN=64, OCV/CPU_FP16)|-|2.922|-| |conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.463|1.469|1.00| |conv::Conv::(GFLOPS=0.420, K=[3 x 3], IN={1, 96, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.459|-| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU)|1.577|1.580|1.00| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 128, 40, 40}, OCN=128, PM=SAME, OCV/CPU_FP16)|-|1.580|-| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU)|1.826|1.818|1.00| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 256, 20, 20}, OCN=256, PM=SAME, OCV/CPU_FP16)|-|1.817|-| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU)|6.541|5.081|1.29| |conv::Conv::(GFLOPS=0.472, K=[3 x 3], IN={1, 512, 10, 10}, OCN=512, PM=SAME, OCV/CPU_FP16)|-|2.809|-| |conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU)|1.912|1.919|1.00| |conv::Conv::(GFLOPS=0.561, K=[3 x 3], IN={1, 128, 38, 50}, OCN=128, PM=SAME, BIAS, OCV/CPU_FP16)|-|1.919|-| |conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|1.961|1.971|0.99| |conv::Conv::(GFLOPS=0.624, K=[3 x 3], IN={1, 128, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|1.961|-| |conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU)|2.317|2.329|0.99| |conv::Conv::(GFLOPS=0.701, K=[3 x 3], IN={1, 128, 38, 50}, OCN=160, PM=SAME, BIAS, OCV/CPU_FP16)|-|2.322|-| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU)|2.920|2.947|0.99| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 64, 104, 104}, OCN=64, P=[1 x 1], OCV/CPU_FP16)|-|2.924|-| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU)|2.467|2.466|1.00| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 128, 52, 52}, OCN=128, P=[1 x 1], OCV/CPU_FP16)|-|2.496|-| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|3.028|2.997|1.01| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 256, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|2.986|-| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU)|4.353|4.355|1.00| |conv::Conv::(GFLOPS=0.798, K=[3 x 3], IN={1, 512, 13, 13}, OCN=512, P=[1 x 1], OCV/CPU_FP16)|-|4.355|-| |conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|2.762|2.793|0.99| |conv::Conv::(GFLOPS=0.830, K=[3 x 3], IN={1, 64, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU_FP16)|-|2.797|-| |conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU)|3.428|3.226|1.06| |conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 192, 38, 38}, OCN=192, PM=SAME, OCV/CPU_FP16)|-|3.223|-| |conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU)|3.967|3.957|1.00| |conv::Conv::(GFLOPS=0.958, K=[3 x 3], IN={1, 384, 19, 19}, OCN=384, PM=SAME, OCV/CPU_FP16)|-|3.960|-| |conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU)|4.806|4.387|1.10| |conv::Conv::(GFLOPS=1.022, K=[3 x 3], IN={1, 576, 19, 19}, OCN=273, PM=SAME, BIAS, OCV/CPU_FP16)|-|4.366|-| |conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|14.509|11.756|1.23| |conv::Conv::(GFLOPS=1.112, K=[3 x 3], IN={1, 512, 10, 10}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|6.510|-| |conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|13.718|13.287|1.03| |conv::Conv::(GFLOPS=1.181, K=[3 x 3], IN={1, 64, 160, 200}, OCN=128, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU_FP16)|-|7.190|-| |conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU)|15.133|14.853|1.02| |conv::Conv::(GFLOPS=1.182, K=[3 x 3], IN={1, 32, 320, 400}, OCN=64, S=[2 x 2], P=[1 x 1], BIAS, OCV/CPU_FP16)|-|8.671|-| |conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU)|41.928|43.328|0.97| |conv::Conv::(GFLOPS=1.195, K=[9 x 9], IN={1, 32, 240, 320}, OCN=3, P=[4 x 4], BIAS, OCV/CPU_FP16)|-|38.072|-| |conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU)|4.409|4.428|1.00| |conv::Conv::(GFLOPS=1.196, K=[3 x 3], IN={1, 384, 26, 26}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|4.427|-| |conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU)|6.144|5.363|1.15| |conv::Conv::(GFLOPS=1.210, K=[3 x 3], IN={1, 32, 256, 256}, OCN=32, PM=SAME, OCV/CPU_FP16)|-|5.368|-| |conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU)|3.926|3.932|1.00| |conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 64, 75, 75}, OCN=192, PM=SAME, BIAS, OCV/CPU_FP16)|-|3.938|-| |conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU)|3.920|3.915|1.00| |conv::Conv::(GFLOPS=1.245, K=[3 x 3], IN={1, 96, 75, 100}, OCN=96, PM=SAME, BIAS, OCV/CPU_FP16)|-|3.950|-| |conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|3.767|3.764|1.00| |conv::Conv::(GFLOPS=1.248, K=[3 x 3], IN={1, 256, 46, 46}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|3.762|-| |conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU)|19.959|13.875|1.44| |conv::Conv::(GFLOPS=1.258, K=[3 x 3], IN={1, 1280, 10, 10}, OCN=546, PM=SAME, BIAS, OCV/CPU_FP16)|-|7.781|-| |conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU)|3.951|3.955|1.00| |conv::Conv::(GFLOPS=1.261, K=[3 x 3], IN={1, 192, 38, 50}, OCN=192, PM=SAME, BIAS, OCV/CPU_FP16)|-|3.969|-| |conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU)|4.050|4.034|1.00| |conv::Conv::(GFLOPS=1.416, K=[3 x 3], IN={1, 128, 62, 82}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.093|-| |conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU)|4.923|4.506|1.09| |conv::Conv::(GFLOPS=1.500, K=[3 x 3], IN={1, 128, 64, 84}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.509|-| |conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU)|4.759|4.476|1.06| |conv::Conv::(GFLOPS=1.586, K=[3 x 3], IN={1, 128, 66, 86}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.447|-| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU)|6.079|5.628|1.08| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 26, 26}, OCN=512, P=[1 x 1], OCV/CPU_FP16)|-|5.625|-| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU)|19.843|17.523|1.13| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 256, 52, 52}, OCN=512, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|8.917|-| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU)|8.334|8.247|1.01| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 13, 13}, OCN=1024, P=[1 x 1], OCV/CPU_FP16)|-|8.246|-| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU)|23.164|18.199|1.27| |conv::Conv::(GFLOPS=1.595, K=[3 x 3], IN={1, 512, 26, 26}, OCN=1024, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|9.305|-| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU)|5.184|5.178|1.00| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 104, 104}, OCN=128, P=[1 x 1], OCV/CPU_FP16)|-|5.149|-| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.990|18.103|0.99| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 64, 208, 208}, OCN=128, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|9.777|-| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU)|4.831|4.522|1.07| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 52, 52}, OCN=256, P=[1 x 1], OCV/CPU_FP16)|-|4.523|-| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU)|17.328|17.319|1.00| |conv::Conv::(GFLOPS=1.596, K=[3 x 3], IN={1, 128, 104, 104}, OCN=256, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|8.948|-| |conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU)|5.944|5.961|1.00| |conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 208, 208}, OCN=64, P=[1 x 1], OCV/CPU_FP16)|-|5.936|-| |conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU)|19.811|20.064|0.99| |conv::Conv::(GFLOPS=1.598, K=[3 x 3], IN={1, 32, 416, 416}, OCN=64, S=[2 x 2], P=[1 x 1], OCV/CPU_FP16)|-|11.705|-| |conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU)|22.398|17.686|1.27| |conv::Conv::(GFLOPS=1.659, K=[3 x 3], IN={1, 960, 10, 10}, OCN=960, PM=SAME, OCV/CPU_FP16)|-|9.859|-| |conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU)|0.416|0.416|1.00| |conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, G=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.417|-| |conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU)|5.356|5.110|1.05| |conv::Conv::(GFLOPS=1.660, K=[3 x 3], IN={1, 128, 75, 75}, OCN=128, PM=SAME, OCV/CPU_FP16)|-|5.114|-| |conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU)|5.092|4.748|1.07| |conv::Conv::(GFLOPS=1.675, K=[3 x 3], IN={1, 128, 68, 88}, OCN=128, BIAS, OCV/CPU_FP16)|-|4.754|-| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU)|0.260|0.229|1.13| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, G=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.229|-| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU)|5.872|5.460|1.08| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 256, 38, 38}, OCN=256, PM=SAME, OCV/CPU_FP16)|-|5.460|-| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU)|0.161|0.161|1.00| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, G=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.161|-| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|7.176|7.175|1.00| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|7.162|-| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU)|7.174|7.185|1.00| |conv::Conv::(GFLOPS=1.704, K=[3 x 3], IN={1, 512, 19, 19}, OCN=512, PM=SAME, OCV/CPU_FP16)|-|7.157|-| |conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU)|5.400|5.180|1.04| |conv::Conv::(GFLOPS=1.766, K=[3 x 3], IN={1, 128, 70, 90}, OCN=128, BIAS, OCV/CPU_FP16)|-|5.201|-| |conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU)|5.330|5.188|1.03| |conv::Conv::(GFLOPS=1.859, K=[3 x 3], IN={1, 128, 72, 92}, OCN=128, BIAS, OCV/CPU_FP16)|-|5.177|-| |conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU)|0.115|0.115|1.00| |conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, G=1024, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|0.115|-| |conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU)|26.156|20.222|1.29| |conv::Conv::(GFLOPS=1.888, K=[3 x 3], IN={1, 1024, 10, 10}, OCN=1024, PM=SAME, OCV/CPU_FP16)|-|11.203|-| |conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU)|5.627|5.543|1.02| |conv::Conv::(GFLOPS=1.954, K=[3 x 3], IN={1, 128, 74, 94}, OCN=128, BIAS, OCV/CPU_FP16)|-|5.506|-| |conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU)|27.925|27.741|1.01| |conv::Conv::(GFLOPS=1.995, K=[9 x 9], IN={1, 3, 320, 400}, OCN=32, P=[4 x 4], BIAS, OCV/CPU_FP16)|-|17.217|-| |conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU)|6.359|6.062|1.05| |conv::Conv::(GFLOPS=2.052, K=[3 x 3], IN={1, 128, 76, 96}, OCN=128, BIAS, OCV/CPU_FP16)|-|6.048|-| |conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU)|6.559|6.322|1.04| |conv::Conv::(GFLOPS=2.100, K=[3 x 3], IN={1, 144, 75, 75}, OCN=144, PM=SAME, OCV/CPU_FP16)|-|6.280|-| |conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU)|6.412|6.200|1.03| |conv::Conv::(GFLOPS=2.153, K=[3 x 3], IN={1, 128, 78, 98}, OCN=128, BIAS, OCV/CPU_FP16)|-|6.197|-| |conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU)|9.167|8.624|1.06| |conv::Conv::(GFLOPS=2.156, K=[3 x 3], IN={1, 576, 19, 19}, OCN=576, PM=SAME, OCV/CPU_FP16)|-|8.626|-| |conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU)|6.755|6.491|1.04| |conv::Conv::(GFLOPS=2.255, K=[3 x 3], IN={1, 128, 80, 100}, OCN=128, BIAS, OCV/CPU_FP16)|-|6.520|-| |conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU)|35.664|34.752|1.03| |conv::Conv::(GFLOPS=2.719, K=[3 x 3], IN={1, 96, 256, 256}, OCN=96, S=[2 x 2], PM=SAME, OCV/CPU_FP16)|-|20.260|-| |conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|9.514|9.414|1.01| |conv::Conv::(GFLOPS=3.319, K=[3 x 3], IN={1, 128, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|9.462|-| |conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|10.631|9.963|1.07| |conv::Conv::(GFLOPS=3.321, K=[3 x 3], IN={1, 64, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|9.935|-| |conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|37.465|36.798|1.02| |conv::Conv::(GFLOPS=3.398, K=[7 x 7], IN={1, 128, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU_FP16)|-|19.569|-| |conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU)|38.157|36.157|1.06| |conv::Conv::(GFLOPS=3.407, K=[3 x 3], IN={1, 512, 19, 19}, OCN=1024, D=[6 x 6], P=[6 x 6], BIAS, OCV/CPU_FP16)|-|18.902|-| |conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|10.356|10.401|1.00| |conv::Conv::(GFLOPS=3.408, K=[3 x 3], IN={1, 256, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|10.360|-| |conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|12.641|12.150|1.04| |conv::Conv::(GFLOPS=4.247, K=[3 x 3], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU_FP16)|-|12.162|-| |conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU)|50.545|50.505|1.00| |conv::Conv::(GFLOPS=4.247, K=[5 x 5], IN={1, 144, 128, 128}, OCN=144, S=[2 x 2], PM=SAME, OCV/CPU_FP16)|-|27.950|-| |conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU)|54.233|49.603|1.09| |conv::Conv::(GFLOPS=4.566, K=[7 x 7], IN={1, 172, 46, 46}, OCN=128, P=[3 x 3], BIAS, OCV/CPU_FP16)|-|26.515|-| |conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|13.779|12.968|1.06| |conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 256, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|12.984|-| |conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|15.809|15.329|1.03| |conv::Conv::(GFLOPS=4.993, K=[3 x 3], IN={1, 512, 46, 46}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|15.433|-| |conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|14.563|14.527|1.00| |conv::Conv::(GFLOPS=4.994, K=[3 x 3], IN={1, 128, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|14.480|-| |conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|16.714|16.484|1.01| |conv::Conv::(GFLOPS=4.997, K=[3 x 3], IN={1, 64, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|16.362|-| |conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU)|77.832|65.729|1.18| |conv::Conv::(GFLOPS=5.780, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, S=[2 x 2], PM=SAME, OCV/CPU_FP16)|-|32.065|-| |conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|21.903|20.386|1.07| |conv::Conv::(GFLOPS=6.116, K=[3 x 3], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU_FP16)|-|20.416|-| |conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU)|20.405|18.148|1.12| |conv::Conv::(GFLOPS=6.118, K=[3 x 3], IN={1, 144, 128, 128}, OCN=144, PM=SAME, OCV/CPU_FP16)|-|18.128|-| |conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|20.334|18.521|1.10| |conv::Conv::(GFLOPS=6.637, K=[3 x 3], IN={1, 256, 75, 75}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|18.495|-| |conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|21.527|19.584|1.10| |conv::Conv::(GFLOPS=6.638, K=[3 x 3], IN={1, 128, 150, 150}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|19.630|-| |conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU)|22.715|20.057|1.13| |conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 150, 200}, OCN=192, PM=SAME, BIAS, OCV/CPU_FP16)|-|20.068|-| |conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|26.228|24.992|1.05| |conv::Conv::(GFLOPS=6.641, K=[3 x 3], IN={1, 64, 300, 300}, OCN=64, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|24.957|-| |conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|21.524|21.581|1.00| |conv::Conv::(GFLOPS=6.814, K=[3 x 3], IN={1, 512, 38, 38}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|21.782|-| |conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU)|34.094|31.964|1.07| |conv::Conv::(GFLOPS=8.025, K=[3 x 3], IN={1, 1024, 19, 19}, OCN=1206, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|31.925|-| |conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU)|28.677|27.813|1.03| |conv::Conv::(GFLOPS=9.986, K=[3 x 3], IN={1, 512, 46, 46}, OCN=512, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|27.808|-| |conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU)|31.274|27.892|1.12| |conv::Conv::(GFLOPS=9.987, K=[3 x 3], IN={1, 256, 92, 92}, OCN=256, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|27.910|-| |conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU)|30.533|30.007|1.02| |conv::Conv::(GFLOPS=9.989, K=[3 x 3], IN={1, 128, 184, 184}, OCN=128, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|30.089|-| |conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU)|39.837|38.312|1.04| |conv::Conv::(GFLOPS=9.993, K=[3 x 3], IN={1, 64, 368, 368}, OCN=64, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|38.477|-| |conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU)|32.480|29.237|1.11| |conv::Conv::(GFLOPS=10.087, K=[3 x 3], IN={1, 576, 38, 50}, OCN=512, PM=SAME, BIAS, OCV/CPU_FP16)|-|29.452|-| |conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU)|33.544|32.832|1.02| |conv::Conv::(GFLOPS=10.701, K=[3 x 3], IN={1, 512, 38, 38}, OCN=804, P=[1 x 1], BIAS, OCV/CPU_FP16)|-|32.784|-| |conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU)|134.481|130.678|1.03| |conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 240, 64, 64}, OCN=240, PM=SAME, OCV/CPU_FP16)|-|70.134|-| |conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU)|127.930|126.530|1.01| |conv::Conv::(GFLOPS=11.797, K=[5 x 5], IN={1, 480, 32, 32}, OCN=480, PM=SAME, OCV/CPU_FP16)|-|65.261|-| |conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU)|201.346|187.007|1.08| |conv::Conv::(GFLOPS=16.987, K=[5 x 5], IN={1, 1152, 16, 16}, OCN=1152, PM=SAME, OCV/CPU_FP16)|-|91.525|-| |conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU)|252.038|245.587|1.03| |conv::Conv::(GFLOPS=23.122, K=[5 x 5], IN={1, 672, 32, 32}, OCN=672, PM=SAME, OCV/CPU_FP16)|-|125.477|-| ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [ ] There is a reference to the original bug report and related work - [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [ ] The feature is well documented and sample code can be built with the project CMake
2 years ago
if (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD || target == DNN_TARGET_CPU_FP16)
{
l1 = 0.02;
lInf = 0.2;
}
else if (target == DNN_TARGET_CUDA_FP16)
{
l1 = 0.018;
lInf = 0.16;
}
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2020040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
{
l1 = 0.018f; lInf = 0.16f;
}
#endif
testONNXModels("tiny_yolo2", pb, l1, lInf, false, true, 1, true, false);
}
TEST_P(Test_ONNX_nets, CNN_MNIST)
{
// output range: [-1952; 6574], after Softmax [0; 1]
testONNXModels("cnn_mnist", pb, default_l1, default_lInf, true);
}
TEST_P(Test_ONNX_nets, MobileNet_v2)
{
// output range: [-166; 317], after Softmax [0; 1]
testONNXModels("mobilenetv2", pb, default_l1, default_lInf, true);
}
TEST_P(Test_ONNX_nets, MobileNet_v2_FP16)
{
testONNXModels("mobilenetv2_fp16", npy, default_l1, default_lInf, true);
}
TEST_P(Test_ONNX_nets, LResNet100E_IR)
{
applyTestTag(
#if defined(OPENCV_32BIT_CONFIGURATION) && defined(HAVE_OPENCL)
CV_TEST_TAG_MEMORY_2GB,
#else
(target == DNN_TARGET_CPU ? CV_TEST_TAG_MEMORY_512MB : CV_TEST_TAG_MEMORY_1GB),
#endif
CV_TEST_TAG_DEBUG_LONG
);
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
}
double l1 = default_l1, lInf = default_lInf;
// output range: [-3; 3]
bool useWinograd = true;
if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16)
{
l1 = 0.009;
lInf = 0.035;
}
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_CPU)
{
l1 = 4.6e-5;
lInf = 1.9e-4;
}
else if (target == DNN_TARGET_CUDA_FP16)
{
l1 = 0.009;
lInf = 0.04;
}
else if (target == DNN_TARGET_CPU_FP16)
{
useWinograd = false;
l1 = 0.009;
lInf = 0.035;
}
testONNXModels("LResNet100E_IR", pb, l1, lInf, false, true, 1, true, useWinograd);
}
TEST_P(Test_ONNX_nets, Emotion_ferplus)
{
#if defined(INF_ENGINE_RELEASE)
if (target == DNN_TARGET_MYRIAD && getInferenceEngineVPUType() == CV_DNN_INFERENCE_ENGINE_VPU_TYPE_MYRIAD_X)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD_X,
backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 ?
CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER :
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH);
#endif
double l1 = default_l1;
double lInf = default_lInf;
bool useWinograd = true;
// Output values are in range [-2.011, 2.111]
if ((backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16) || (target == DNN_TARGET_CUDA_FP16))
l1 = 0.007;
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target == DNN_TARGET_OPENCL_FP16)
{
l1 = 0.021;
lInf = 0.034;
}
else if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && (target == DNN_TARGET_CPU || target == DNN_TARGET_OPENCL)) {
l1 = 2.4e-4;
lInf = 6e-4;
}
else if (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_CPU_FP16)
{
useWinograd = false;
l1 = 0.007;
}
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_GE(2020040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
{
l1 = 0.013f; lInf = 0.035f;
}
#endif
testONNXModels("emotion_ferplus", pb, l1, lInf, false, true, 1, true, useWinograd);
}
TEST_P(Test_ONNX_nets, Inception_v2)
{
testONNXModels("inception_v2", pb, default_l1, default_lInf, true);
}
TEST_P(Test_ONNX_nets, DenseNet121)
{
applyTestTag(CV_TEST_TAG_MEMORY_512MB);
// output range: [-87; 138], after Softmax [0; 1]
testONNXModels("densenet121", pb, default_l1, default_lInf, true, target != DNN_TARGET_MYRIAD);
}
TEST_P(Test_ONNX_nets, Inception_v1)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if ((backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 ||
backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH) && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD);
#endif
testONNXModels("inception_v1", pb);
}
TEST_P(Test_ONNX_nets, Shufflenet)
{
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
{
if (target == DNN_TARGET_OPENCL_FP16) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_OPENCL) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_OPENCL, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
if (target == DNN_TARGET_MYRIAD) applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
}
#endif
testONNXModels("shufflenet", pb);
}
TEST_P(Test_ONNX_nets, Resnet34_kinetics)
{
applyTestTag(CV_TEST_TAG_DEBUG_VERYLONG);
#if defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2022010000)
// IE exception: Failed to allocate graph: MYRIAD device is not opened
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
// accuracy
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
applyTestTag(target == DNN_TARGET_OPENCL ? CV_TEST_TAG_DNN_SKIP_IE_OPENCL : CV_TEST_TAG_DNN_SKIP_IE_OPENCL_FP16,
CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION
);
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_EQ(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH)
{
// IE exception: Function contains several inputs and outputs with one friendly name!
if (target == DNN_TARGET_MYRIAD)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_MYRIAD, CV_TEST_TAG_DNN_SKIP_IE_NGRAPH, CV_TEST_TAG_DNN_SKIP_IE_VERSION);
}
#elif defined(INF_ENGINE_RELEASE) && INF_ENGINE_VER_MAJOR_LT(2021040000)
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER); // Only CPU on DLIE backend is supported
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target != DNN_TARGET_CPU)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NGRAPH); // Only CPU on DLIE backend is supported
#endif
if (backend == DNN_BACKEND_OPENCV && target != DNN_TARGET_CPU)
throw SkipTestException("Only CPU is supported"); // FIXIT use tags
if (backend == DNN_BACKEND_VKCOM)
applyTestTag(CV_TEST_TAG_DNN_SKIP_VULKAN);
String onnxmodel = findDataFile("dnn/resnet-34_kinetics.onnx", false);
Mat image0 = imread(findDataFile("dnn/dog416.png"));
Mat image1 = imread(findDataFile("dnn/street.png"));
Mat ref0 = blobFromNPY(_tf("data/output_kinetics0.npy"));
Mat ref1 = blobFromNPY(_tf("data/output_kinetics1.npy"));
std::vector<Mat> images_0(16, image0);
std::vector<Mat> images_1(16, image1);
Mat blob0 = blobFromImages(images_0, 1.0, Size(112, 112), Scalar(114.7748, 107.7354, 99.4750), true, true);
Mat blob1 = blobFromImages(images_1, 1.0, Size(112, 112), Scalar(114.7748, 107.7354, 99.4750), true, true);
Net permute;
LayerParams lp;
int order[] = {1, 0, 2, 3};
lp.set("order", DictValue::arrayInt<int*>(&order[0], 4));
permute.addLayerToPrev("perm", "Permute", lp);
permute.setPreferableBackend(backend);
permute.setPreferableTarget(target);
permute.setInput(blob0);
Mat input0 = permute.forward().clone();
permute.setInput(blob1);
Mat input1 = permute.forward().clone();
int dims[] = {1, 3, 16, 112, 112};
input0 = input0.reshape(0, 5, &dims[0]);
input1 = input1.reshape(0, 5, &dims[0]);
Net net = readNetFromONNX(onnxmodel);
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
// output range [-5, 11]
float l1 = 0.0013;
float lInf = 0.009;
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && target == DNN_TARGET_OPENCL_FP16)
{
l1 = 0.02;
lInf = 0.07;
}
if (target == DNN_TARGET_CUDA_FP16)
{
l1 = 0.01;
lInf = 0.06;
}
testInputShapes(net, {input0});
checkBackend(&input0, &ref0);
net.setInput(input0);
Mat out = net.forward().clone();
normAssert(ref0, out, "", l1, lInf);
checkBackend(&input1, &ref1);
net.setInput(input1);
out = net.forward().clone();
normAssert(ref1, out, "", l1, lInf);
expectNoFallbacksFromIE(net);
}
TEST_P(Test_ONNX_layers, CumSum)
{
testONNXModels("cumsum_1d_exclusive_1");
testONNXModels("cumsum_1d_reverse");
testONNXModels("cumsum_1d_exclusive_1_reverse");
testONNXModels("cumsum_2d_dim_1");
testONNXModels("cumsum_3d_dim_2");
}
static void testYOLO(const std::string& weightPath, const std::vector<int>& refClassIds,
const std::vector<float>& refScores, const std::vector<Rect2d>& refBoxes,
Image2BlobParams imgParams, float conf_threshold = 0.3, float iou_threshold = 0.5,
double scores_diff = 1e-5, double boxes_iou_diff = 1e-4, const std::string test_name = "")
{
std::string imgPath = _tf("../dog_orig_size.png");
Mat img = imread(imgPath);
Mat inp = blobFromImageWithParams(img, imgParams);
Net net = readNet(weightPath);
net.setInput(inp);
std::vector<Mat> outs;
net.forward(outs, net.getUnconnectedOutLayersNames());
// Retrieve
std::vector<int> keep_classIds;
std::vector<float> keep_confidences;
std::vector<Rect2d> keep_boxes;
yoloPostProcessing(outs, keep_classIds, keep_confidences, keep_boxes, conf_threshold, iou_threshold, test_name);
normAssertDetections(
refClassIds, refScores, refBoxes,
keep_classIds, keep_confidences, keep_boxes,
"", 0.0, scores_diff, boxes_iou_diff);
}
void yoloPostProcessing(
std::vector<Mat>& outs,
std::vector<int>& keep_classIds,
std::vector<float>& keep_confidences,
std::vector<Rect2d>& keep_boxes,
float conf_threshold,
float iou_threshold,
const std::string& test_name
){
// Retrieve
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect2d> boxes;
if (test_name == "yolov8"){
cv::transposeND(outs[0], {0, 2, 1}, outs[0]);
}
// each row is [cx, cy, w, h, conf_obj, conf_class1, ..., conf_class80]
for (auto preds : outs){
preds = preds.reshape(1, preds.size[1]); // [1, 8400, 85] -> [8400, 85]
for (int i = 0; i < preds.rows; ++i)
{
// filter out non objects
float obj_conf = (test_name != "yolov8") ? preds.at<float>(i, 4) : 1.0f;
if (obj_conf < conf_threshold)
continue;
Mat scores = preds.row(i).colRange((test_name != "yolov8") ? 5 : 4, preds.cols);
double conf;
Point maxLoc;
minMaxLoc(scores, 0, &conf, 0, &maxLoc);
conf = (test_name != "yolov8") ? conf * obj_conf : conf;
if (conf < conf_threshold)
continue;
// get bbox coords
float* det = preds.ptr<float>(i);
double cx = det[0];
double cy = det[1];
double w = det[2];
double h = det[3];
// [x1, y1, x2, y2]
boxes.push_back(Rect2d(cx - 0.5 * w, cy - 0.5 * h,
cx + 0.5 * w, cy + 0.5 * h));
classIds.push_back(maxLoc.x);
confidences.push_back(conf);
}
}
// NMS
std::vector<int> keep_idx;
NMSBoxes(boxes, confidences, conf_threshold, iou_threshold, keep_idx);
for (auto i : keep_idx)
{
keep_classIds.push_back(classIds[i]);
keep_confidences.push_back(confidences[i]);
keep_boxes.push_back(boxes[i]);
}
}
TEST_P(Test_ONNX_nets, YOLOX)
{
std::string weightPath = _tf("models/yolox_s_inf_decoder.onnx", false);
Size targetSize{640, 640};
float conf_threshold = 0.50;
float iou_threshold = 0.50;
std::vector<int> refClassIds{1, 16, 7};
std::vector<float> refScores{0.9649f, 0.9163f, 0.6879f};
std::vector<Rect2d> refBoxes{
Rect2d(105.5384, 179.4100, 470.6339, 428.5553),
Rect2d(111.4482, 263.4098, 258.7438, 526.1140),
Rect2d(389.1421, 143.9286, 577.9495, 222.0294)
};
Image2BlobParams imgParams(
Scalar::all(1),
targetSize,
Scalar::all(0),
true,
CV_32F,
DNN_LAYOUT_NCHW,
DNN_PMODE_LETTERBOX,
Scalar::all(114)
);
testYOLO(
weightPath, refClassIds, refScores, refBoxes,
imgParams, conf_threshold, iou_threshold,
1.0e-4, 1.0e-4);
}
TEST_P(Test_ONNX_nets, YOLOv8)
{
std::string weightPath = _tf("models/yolov8n.onnx", false);
Size targetSize{640, 640};
float conf_threshold = 0.25;
float iou_threshold = 0.50;
std::vector<int> refClassIds{16, 1, 2};
std::vector<float> refScores{0.9332f, 0.8959f, 0.6157f};
// [x1, y1, x2, y2]
std::vector<Rect2d> refBoxes{
Rect2d(108.8965, 261.9094, 257.1633, 530.3049),
Rect2d(110.4020, 192.9843, 473.4418, 429.5965),
Rect2d(389.1603, 143.2506, 577.3542, 223.0615),
};
Image2BlobParams imgParams(
Scalar::all(1/255.0),
targetSize,
Scalar::all(0),
true,
CV_32F,
DNN_LAYOUT_NCHW,
DNN_PMODE_LETTERBOX,
Scalar::all(114)
);
testYOLO(
weightPath, refClassIds, refScores, refBoxes,
imgParams, conf_threshold, iou_threshold,
1.0e-4, 1.0e-4, "yolov8");
}
// This test is mainly to test:
// 1. identity node with constant input
// 2. limited support to range operator (all inputs are constant)
// 3. parseExpand with multiple broadcast axes
// 4. 1D mat dimension issue with the output of range operator
TEST_P(Test_ONNX_nets, YOLOv7)
{
std::string weightPath = _tf("models/yolov7_not_simplified.onnx", false);
// Reference, which is collected with input size of 640x640
std::vector<int> refClassIds{1, 16, 7};
std::vector<float> refScores{0.9614331f, 0.9589417f, 0.8679074f};
// [x1, y1, x2, y2] x 3
std::vector<Rect2d> refBoxes{Rect2d(105.973236f, 150.16716f, 472.59012f, 466.48834f),
Rect2d(109.97953f, 246.17862f, 259.83676f, 600.76624f),
Rect2d(385.96185f, 83.02809f, 576.07355f, 189.82793f)};
Size targetSize{640, 640};
Image2BlobParams imgParams(
Scalar::all(1/255.0),
targetSize,
Scalar::all(0),
true,
CV_32F,
DNN_LAYOUT_NCHW,
DNN_PMODE_NULL,
Scalar::all(0)
);
testYOLO(weightPath, refClassIds, refScores, refBoxes, imgParams);
}
TEST_P(Test_ONNX_nets, YOLOv6)
{
std::string weightPath = _tf("models/yolov6n.onnx", false);
Size targetSize{640, 640};
float conf_threshold = 0.30;
float iou_threshold = 0.50;
std::vector<int> refClassIds{1, 16, 7, 1};
std::vector<float> refScores{0.95031f, 0.87123f, 0.65453f, 0.34142f};
// [x1, y1, x2, y2] x 3
std::vector<Rect2d> refBoxes{Rect2d(98.84, 177.91, 473.29, 431.19),
Rect2d(109.80, 265.50, 258.86, 531.97),
Rect2d(387.79, 141.61, 576.98, 223.52),
Rect2d(105.62, 199.24, 218.37, 389.84),
};
Image2BlobParams imgParams(
Scalar::all(1/255.0),
targetSize,
Scalar::all(0),
true,
CV_32F,
DNN_LAYOUT_NCHW,
DNN_PMODE_LETTERBOX,
Scalar::all(114)
);
testYOLO(
weightPath, refClassIds, refScores, refBoxes,
imgParams, conf_threshold, iou_threshold,
1.0e-4, 1.0e-3);
}
TEST_P(Test_ONNX_nets, YOLOv5n)
{
std::string weightPath = findDataFile("dnn/yolov5n.onnx", false);
// Reference, which is collected with input size of 640x640
std::vector<int> refClassIds{16, 2, 1};
std::vector<float> refScores{0.749053f, 0.616853f, 0.32506f};
// [x1, y1, x2, y2] x 4
std::vector<Rect2d> refBoxes{Rect2d(108.088f, 239.293f, 266.196f, 607.658f),
Rect2d(392.028f, 89.9233f, 579.152f, 190.447f),
Rect2d(120.278f, 159.76, 214.481f, 241.473f)};
Size targetSize{640, 640};
Image2BlobParams imgParams(
Scalar::all(1/255.0),
targetSize,
Scalar::all(0),
true,
CV_32F,
DNN_LAYOUT_NCHW,
DNN_PMODE_NULL,
Scalar::all(0)
);
testYOLO(weightPath, refClassIds, refScores, refBoxes, imgParams);
}
2 years ago
TEST_P(Test_ONNX_layers, Tile)
{
testONNXModels("tile", pb);
}
TEST_P(Test_ONNX_layers, Gelu)
{
testONNXModels("gelu");
testONNXModels("gelu_approximation");
}
TEST_P(Test_ONNX_layers, OpenAI_CLIP_head)
{
testONNXModels("clip-vit-base-head");
}
TEST_P(Test_ONNX_layers, where_node)
{
testONNXModels("where_layer");
}
TEST_P(Test_ONNX_layers, Gemm_all_attributes) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_all_attributes", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_alpha) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_alpha", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_beta) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_beta", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_default_matrix_bias) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_default_matrix_bias", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_default_no_bias) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_default_no_bias", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_default_scalar_bias) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_default_scalar_bias", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_default_single_elem_vector_bias) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_default_single_elem_vector_bias", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_default_vector_bias) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_default_vector_bias", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_default_zero_bias) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_default_zero_bias", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_transposeA) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_transposeA", pb, 0, 0, false, true, 2);
}
TEST_P(Test_ONNX_layers, Gemm_transposeB) {
dnn: add gemm_layer in place of fully_connected_layer for onnx models (#23897) * first commit * turned C from input to constant; force C constant in impl; better handling 0d/1d cases * integrate with gemm from ficus nn * fix const inputs * adjust threshold for int8 tryQuantize * adjust threshold for int8 quantized 2 * support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet * add gemm perf against innerproduct * add perf tests for innerproduct with bias * fix perf * add memset * renamings for next step * add dedicated perf gemm * add innerproduct in perf_gemm * remove gemm and innerproduct perf tests from perf_layer * add perf cases for vit sizes; prepack constants * remove batched gemm; fix wrong trans; optimize KC * remove prepacking for const A; several fixes for const B prepacking * add todos and gemm expression * add optimized branch for avx/avx2 * trigger build * update macros and signature * update signature * fix macro * fix bugs for neon aarch64 & x64 * add backends: cuda, cann, inf_ngraph and vkcom * fix cuda backend * test commit for cuda * test cuda backend * remove debug message from cuda backend * use cpu dispatcher * fix neon macro undef in dispatcher * fix dispatcher * fix inner kernel for neon aarch64 * fix compiling issue on armv7; try fixing accuracy issue on other platforms * broadcast C with beta multiplied; improve func namings * fix bug for avx and avx2 * put all platform-specific kernels in dispatcher * fix typos * attempt to fix compile issues on x64 * run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon * fix typo * quick fix: add macros for pack4 * quick fix: use vmlaq_f32 for armv7 * quick fix for missing macro of fast gemm pack f32 4 * disable conformance tests when optimized branches are not supported * disable perf tests when optimized branches are not supported * decouple cv_try_neon and cv_neon_aarch64 * drop googlenet_2023; add fastGemmBatched * fix step in fastGemmBatched * cpu: fix initialization ofb; gpu: support batch * quick followup fix for cuda * add default kernels * quick followup fix to avoid macro redef * optmized kernels for lasx * resolve mis-alignment; remove comments * tune performance for x64 platform * tune performance for neon aarch64 * tune for armv7 * comment time consuming tests * quick follow-up fix
1 year ago
testONNXModels("test_gemm_transposeB", pb, 0, 0, false, true, 2);
}
// Note: These tests are converted from onnx/onnx so that they have constant shape as input.
// TODO: They can be moved into conformance tests once dynamic input is properly supported.
TEST_P(Test_ONNX_layers, Expand_dim_changed) {
testONNXModels("test_expand_dim_changed", pb, 0, 0, false, true, 1);
}
TEST_P(Test_ONNX_layers, Expand_dim_unchanged) {
testONNXModels("test_expand_dim_unchanged", pb, 0, 0, false, true, 1);
}
TEST_P(Test_ONNX_layers, Expand_shape_model1) {
testONNXModels("test_expand_shape_model1", pb, 0, 0, false, true, 1);
}
TEST_P(Test_ONNX_layers, Expand_shape_model2) {
testONNXModels("test_expand_shape_model2", pb, 0, 0, false, true, 1);
}
TEST_P(Test_ONNX_layers, Expand_shape_model3) {
testONNXModels("test_expand_shape_model3", pb, 0, 0, false, true, 1);
}
TEST_P(Test_ONNX_layers, Expand_shape_model4) {
testONNXModels("test_expand_shape_model4", pb, 0, 0, false, true, 1);
}
Merge pull request #24476 from fengyuentau:attention_layer dnn: add attention layer #24476 Resolves #24609 Merge with: https://github.com/opencv/opencv_extra/pull/1128. Attention operator spec from onnxruntime: https://github.com/microsoft/onnxruntime/blob/v1.16.1/docs/ContribOperators.md#com.microsoft.Attention. TODO: - [x] benchmark (before this PR vs. with this PR vs. ORT). - [x] Layer fusion: Take care Slice with end=INT64_MAX. - [x] Layer fusion: match more potential attention (VIT) patterns. - [x] Single-head attention is supported. - [x] Test AttentionSubgraph fusion. - [x] Add acc tests for VIT_B_32 and VitTrack - [x] Add perf tests for VIT_B_32 and VitTrack ## Benchmarks Platform: Macbook Air M1. ### Attention Subgraph Input scale: [1, 197, 768]. | | mean (ms) | median (ms) | min (ms) | | ---------------------- | --------- | ----------- | -------- | | w/ Attention (this PR) | 3.75 | 3.68 | 3.22 | | w/o Attention | 9.06 | 9.01 | 8.24 | | ORT (python) | 4.32 | 2.63 | 2.50 | ### ViTs All data in millisecond (ms). | ViTs | With Attention | Without Attention | ORT | | -------- | -------------- | ----------------- | ------ | | vit_b_16 | 302.77 | 365.35 | 109.70 | | vit_b_32 | 89.92 | 116.22 | 30.36 | | vit_l_16 | 1593.32 | 1730.74 | 419.92 | | vit_l_32 | 468.11 | 577.41 | 134.12 | | VitTrack | 3.80 | 3.87 | 2.25 | ### Pull Request Readiness Checklist See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request - [x] I agree to contribute to the project under Apache 2 License. - [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV - [x] The PR is proposed to the proper branch - [x] There is a reference to the original bug report and related work - [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable Patch to opencv_extra has the same branch name. - [x] The feature is well documented and sample code can be built with the project CMake
12 months ago
TEST_P(Test_ONNX_layers, Attention) {
testONNXModels("attention");
}
TEST_P(Test_ONNX_layers, AttentionSingleHead) {
testONNXModels("attention_single_head");
}
TEST_P(Test_ONNX_nets, ViT_B_32) {
applyTestTag(CV_TEST_TAG_LONG, CV_TEST_TAG_DEBUG_LONG);
if (backend == DNN_BACKEND_CUDA && target == DNN_TARGET_CUDA_FP16)
{
// does not pass test for now
applyTestTag(CV_TEST_TAG_DNN_SKIP_CUDA_FP16);
}
const std::string model_path = _tf("models/vit_b_32.onnx", false);
auto net = readNet(model_path);
ASSERT_FALSE(net.empty());
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
auto image = imread(_tf("../googlenet_0.png"));
auto blob = blobFromImage(image, 1.f, Size(224, 224));
auto ref = blobFromNPY(_tf("data/output_vit_b_32.npy"));
checkBackend(&blob, &ref);
net.setInput(blob);
auto out = net.forward();
normAssert(ref, out, "ViTB_32", default_l1, default_lInf);
}
TEST_P(Test_ONNX_nets, VitTrack) {
auto image = imread(_tf("../dog_orig_size.png"));
auto input0 = blobFromImage(image, 1.f, Size(128, 128));
auto input1 = blobFromImage(image, 1.f, Size(256, 256));
auto net = readNet(_tf("models/object_tracking_vittrack_2023sep.onnx", false));
net.setInput(input0, "template");
net.setInput(input1, "search");
std::vector<std::string> output_names{"output1", "output2", "output3"};
std::vector<Mat> outputs;
net.forward(outputs, output_names);
auto ref_output1 = blobFromNPY(_tf("data/output_object_tracking_vittrack_2023sep_0.npy"));
auto ref_output2 = blobFromNPY(_tf("data/output_object_tracking_vittrack_2023sep_1.npy"));
auto ref_output3 = blobFromNPY(_tf("data/output_object_tracking_vittrack_2023sep_2.npy"));
normAssert(ref_output1, outputs[0], "VitTrack output1");
normAssert(ref_output2, outputs[1], "VitTrack output2");
normAssert(ref_output3, outputs[2], "VitTrack output3");
}
INSTANTIATE_TEST_CASE_P(/**/, Test_ONNX_nets, dnnBackendsAndTargets());
}} // namespace