Chiebot-Mirror
/
opencv
mirror of https://github.com/opencv/opencv.git
8
0
Fork 0
Code Issues Projects Releases Wiki Activity

Merge pull request #10992 from dkurt:dnn_opencl_tests

Browse Source
pull/11047/head^2
Alexander Alekhin 7 years ago
parent 687394fa07 0f01b40dd5
commit 5b868ccd82
11 changed files with 258 additions and 476 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 3
      modules/dnn/src/layers/convolution_layer.cpp
  2. 5
      modules/dnn/src/layers/fully_connected_layer.cpp
  3. 5
      modules/dnn/src/layers/lrn_layer.cpp
  4. 4
      modules/dnn/src/layers/pooling_layer.cpp
  5. 5
      modules/dnn/src/layers/softmax_layer.cpp
  6. 3
      modules/dnn/test/test_backends.cpp
  7. 172
      modules/dnn/test/test_caffe_importer.cpp
  8. 4
      modules/dnn/test/test_googlenet.cpp
  9. 19
      modules/dnn/test/test_precomp.hpp
  10. 263
      modules/dnn/test/test_tf_importer.cpp
  11. 251
      modules/dnn/test/test_torch_importer.cpp

3
modules/dnn/src/layers/convolution_layer.cpp
Unescape View File

@ -273,6 +273,9 @@ public:
for(int i = 0; i < outCn; i++ )
biasvec[i] = biasMat.at<float>(i);
}
#ifdef HAVE_OPENCL
convolutionOp.release();
#endif
}
bool setActivation(const Ptr<ActivationLayer>& layer)

5
modules/dnn/src/layers/fully_connected_layer.cpp
Unescape View File

@ -267,6 +267,11 @@ public:
};
#ifdef HAVE_OPENCL
void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs)
{
innerProductOp.release();
}
bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, InputArrayOfArrays internals)
{
std::vector<UMat> inputs;

5
modules/dnn/src/layers/lrn_layer.cpp
Unescape View File

@ -96,6 +96,11 @@ public:
}
#ifdef HAVE_OPENCL
void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs)
{
lrnOp.release();
}
bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, OutputArrayOfArrays internals)
{
std::vector<UMat> inputs;

4
modules/dnn/src/layers/pooling_layer.cpp
Unescape View File

@ -127,6 +127,10 @@ public:
}
getConvPoolPaddings(inp, out, kernel, stride, padMode, Size(1, 1), pad);
#ifdef HAVE_OPENCL
poolOp.release();
#endif
}
virtual bool supportBackend(int backendId)

5
modules/dnn/src/layers/softmax_layer.cpp
Unescape View File

@ -94,6 +94,11 @@ public:
}
#ifdef HAVE_OPENCL
virtual void finalize(const std::vector<Mat*> &inputs, std::vector<Mat> &outputs)
{
softmaxOp.release();
}
bool forward_ocl(InputArrayOfArrays inps, OutputArrayOfArrays outs, OutputArrayOfArrays itns)
{
std::vector<UMat> inputs;

3
modules/dnn/test/test_backends.cpp
Unescape View File

@ -10,9 +10,6 @@
namespace opencv_test { namespace {
CV_ENUM(DNNBackend, DNN_BACKEND_DEFAULT, DNN_BACKEND_HALIDE, DNN_BACKEND_INFERENCE_ENGINE)
CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
static void loadNet(const std::string& weights, const std::string& proto,
const std::string& framework, Net* net)
{

172
modules/dnn/test/test_caffe_importer.cpp
Unescape View File

@ -42,8 +42,6 @@
#include "test_precomp.hpp"
#include "npy_blob.hpp"
#include <opencv2/dnn/shape_utils.hpp>
#include <opencv2/core/ocl.hpp>
#include <opencv2/ts/ocl_test.hpp>
namespace opencv_test { namespace {
@ -83,10 +81,10 @@ TEST(Test_Caffe, read_googlenet)
ASSERT_FALSE(net.empty());
}
typedef testing::TestWithParam<bool> Reproducibility_AlexNet;
typedef testing::TestWithParam<tuple<bool, DNNTarget> > Reproducibility_AlexNet;
TEST_P(Reproducibility_AlexNet, Accuracy)
{
bool readFromMemory = GetParam();
bool readFromMemory = get<0>(GetParam());
Net net;
{
const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false);
@ -106,42 +104,7 @@ TEST_P(Reproducibility_AlexNet, Accuracy)
ASSERT_FALSE(net.empty());
}
Mat sample = imread(_tf("grace_hopper_227.png"));
ASSERT_TRUE(!sample.empty());
net.setInput(blobFromImage(sample, 1.0f, Size(227, 227), Scalar(), false), "data");
Mat out = net.forward("prob");
Mat ref = blobFromNPY(_tf("caffe_alexnet_prob.npy"));
normAssert(ref, out);
}
INSTANTIATE_TEST_CASE_P(Test_Caffe, Reproducibility_AlexNet, testing::Bool());
typedef testing::TestWithParam<bool> Reproducibility_OCL_AlexNet;
OCL_TEST_P(Reproducibility_OCL_AlexNet, Accuracy)
{
bool readFromMemory = GetParam();
Net net;
{
const string proto = findDataFile("dnn/bvlc_alexnet.prototxt", false);
const string model = findDataFile("dnn/bvlc_alexnet.caffemodel", false);
if (readFromMemory)
{
string dataProto;
ASSERT_TRUE(readFileInMemory(proto, dataProto));
string dataModel;
ASSERT_TRUE(readFileInMemory(model, dataModel));
net = readNetFromCaffe(dataProto.c_str(), dataProto.size(),
dataModel.c_str(), dataModel.size());
}
else
net = readNetFromCaffe(proto, model);
ASSERT_FALSE(net.empty());
}
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
net.setPreferableTarget(get<1>(GetParam()));
Mat sample = imread(_tf("grace_hopper_227.png"));
ASSERT_TRUE(!sample.empty());
@ -152,7 +115,7 @@ OCL_TEST_P(Reproducibility_OCL_AlexNet, Accuracy)
normAssert(ref, out);
}
OCL_INSTANTIATE_TEST_CASE_P(Test_Caffe, Reproducibility_OCL_AlexNet, testing::Bool());
INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_AlexNet, Combine(testing::Bool(), availableDnnTargets()));
#if !defined(_WIN32) || defined(_WIN64)
TEST(Reproducibility_FCN, Accuracy)
@ -207,43 +170,14 @@ TEST(Reproducibility_SSD, Accuracy)
normAssert(ref, out);
}
TEST(Reproducibility_MobileNet_SSD, Accuracy)
{
const string proto = findDataFile("dnn/MobileNetSSD_deploy.prototxt", false);
const string model = findDataFile("dnn/MobileNetSSD_deploy.caffemodel", false);
Net net = readNetFromCaffe(proto, model);
Mat sample = imread(_tf("street.png"));
Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
net.setInput(inp);
Mat out = net.forward();
Mat ref = blobFromNPY(_tf("mobilenet_ssd_caffe_out.npy"));
normAssert(ref, out);
// Check that detections aren't preserved.
inp.setTo(0.0f);
net.setInput(inp);
out = net.forward();
const int numDetections = out.size[2];
ASSERT_NE(numDetections, 0);
for (int i = 0; i < numDetections; ++i)
{
float confidence = out.ptr<float>(0, 0, i)[2];
ASSERT_EQ(confidence, 0);
}
}
OCL_TEST(Reproducibility_MobileNet_SSD, Accuracy)
typedef testing::TestWithParam<DNNTarget> Reproducibility_MobileNet_SSD;
TEST_P(Reproducibility_MobileNet_SSD, Accuracy)
{
const string proto = findDataFile("dnn/MobileNetSSD_deploy.prototxt", false);
const string model = findDataFile("dnn/MobileNetSSD_deploy.caffemodel", false);
Net net = readNetFromCaffe(proto, model);
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
net.setPreferableTarget(GetParam());
Mat sample = imread(_tf("street.png"));
@ -258,38 +192,39 @@ OCL_TEST(Reproducibility_MobileNet_SSD, Accuracy)
inp.setTo(0.0f);
net.setInput(inp);
out = net.forward();
out = out.reshape(1, out.total() / 7);
const int numDetections = out.size[2];
const int numDetections = out.rows;
ASSERT_NE(numDetections, 0);
for (int i = 0; i < numDetections; ++i)
{
float confidence = out.ptr<float>(0, 0, i)[2];
float confidence = out.ptr<float>(i)[2];
ASSERT_EQ(confidence, 0);
}
}
TEST(Reproducibility_ResNet50, Accuracy)
{
Net net = readNetFromCaffe(findDataFile("dnn/ResNet-50-deploy.prototxt", false),
findDataFile("dnn/ResNet-50-model.caffemodel", false));
Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(224,224), Scalar(), false);
ASSERT_TRUE(!input.empty());
net.setInput(input);
Mat out = net.forward();
Mat ref = blobFromNPY(_tf("resnet50_prob.npy"));
normAssert(ref, out);
// Check batching mode.
ref = ref.reshape(1, numDetections);
inp = blobFromImages(std::vector<Mat>(2, sample), 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
net.setInput(inp);
Mat outBatch = net.forward();
// Output blob has a shape 1x1x2Nx7 where N is a number of detection for
// a single sample in batch. The first numbers of detection vectors are batch id.
outBatch = outBatch.reshape(1, outBatch.total() / 7);
EXPECT_EQ(outBatch.rows, 2 * numDetections);
normAssert(outBatch.rowRange(0, numDetections), ref);
normAssert(outBatch.rowRange(numDetections, 2 * numDetections).colRange(1, 7), ref.colRange(1, 7));
}
INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_MobileNet_SSD, availableDnnTargets());
OCL_TEST(Reproducibility_ResNet50, Accuracy)
typedef testing::TestWithParam<DNNTarget> Reproducibility_ResNet50;
TEST_P(Reproducibility_ResNet50, Accuracy)
{
Net net = readNetFromCaffe(findDataFile("dnn/ResNet-50-deploy.prototxt", false),
findDataFile("dnn/ResNet-50-model.caffemodel", false));
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
int targetId = GetParam();
net.setPreferableTarget(targetId);
Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(224,224), Scalar(), false);
ASSERT_TRUE(!input.empty());
@ -300,52 +235,46 @@ OCL_TEST(Reproducibility_ResNet50, Accuracy)
Mat ref = blobFromNPY(_tf("resnet50_prob.npy"));
normAssert(ref, out);
UMat out_umat;
net.forward(out_umat);
normAssert(ref, out_umat, "out_umat");
std::vector<UMat> out_umats;
net.forward(out_umats);
normAssert(ref, out_umats[0], "out_umat_vector");
}
TEST(Reproducibility_SqueezeNet_v1_1, Accuracy)
{
Net net = readNetFromCaffe(findDataFile("dnn/squeezenet_v1.1.prototxt", false),
findDataFile("dnn/squeezenet_v1.1.caffemodel", false));
Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false);
ASSERT_TRUE(!input.empty());
net.setInput(input);
Mat out = net.forward();
if (targetId == DNN_TARGET_OPENCL)
{
UMat out_umat;
net.forward(out_umat);
normAssert(ref, out_umat, "out_umat");
Mat ref = blobFromNPY(_tf("squeezenet_v1.1_prob.npy"));
normAssert(ref, out);
std::vector<UMat> out_umats;
net.forward(out_umats);
normAssert(ref, out_umats[0], "out_umat_vector");
}
}
INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_ResNet50, availableDnnTargets());
OCL_TEST(Reproducibility_SqueezeNet_v1_1, Accuracy)
typedef testing::TestWithParam<DNNTarget> Reproducibility_SqueezeNet_v1_1;
TEST_P(Reproducibility_SqueezeNet_v1_1, Accuracy)
{
Net net = readNetFromCaffe(findDataFile("dnn/squeezenet_v1.1.prototxt", false),
findDataFile("dnn/squeezenet_v1.1.caffemodel", false));
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
int targetId = GetParam();
net.setPreferableTarget(targetId);
Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false);
ASSERT_TRUE(!input.empty());
// Firstly set a wrong input blob and run the model to receive a wrong output.
net.setInput(input * 2.0f);
Mat out = net.forward();
// Then set a correct input blob to check CPU->GPU synchronization is working well.
Mat out;
if (targetId == DNN_TARGET_OPENCL)
{
// Firstly set a wrong input blob and run the model to receive a wrong output.
// Then set a correct input blob to check CPU->GPU synchronization is working well.
net.setInput(input * 2.0f);
out = net.forward();
}
net.setInput(input);
out = net.forward();
Mat ref = blobFromNPY(_tf("squeezenet_v1.1_prob.npy"));
normAssert(ref, out);
}
INSTANTIATE_TEST_CASE_P(/**/, Reproducibility_SqueezeNet_v1_1, availableDnnTargets());
TEST(Reproducibility_AlexNet_fp16, Accuracy)
{
@ -456,7 +385,6 @@ TEST(Test_Caffe, multiple_inputs)
normAssert(out, first_image + second_image);
}
CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
typedef testing::TestWithParam<tuple<std::string, DNNTarget> > opencv_face_detector;
TEST_P(opencv_face_detector, Accuracy)
{

4
modules/dnn/test/test_googlenet.cpp
Unescape View File

@ -77,6 +77,10 @@ OCL_TEST(Reproducibility_GoogLeNet, Accuracy)
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
// Initialize network for a single image in the batch but test with batch size=2.
net.setInput(blobFromImage(Mat(224, 224, CV_8UC3)));
net.forward();
std::vector<Mat> inpMats;
inpMats.push_back( imread(_tf("googlenet_0.png")) );
inpMats.push_back( imread(_tf("googlenet_1.png")) );

19
modules/dnn/test/test_precomp.hpp
Unescape View File

@ -44,12 +44,31 @@
#include "opencv2/ts.hpp"
#include "opencv2/ts/ts_perf.hpp"
#include "opencv2/core/utility.hpp"
#include "opencv2/core/ocl.hpp"
#include "opencv2/dnn.hpp"
#include "test_common.hpp"
namespace opencv_test {
using namespace cv::dnn;
CV_ENUM(DNNBackend, DNN_BACKEND_DEFAULT, DNN_BACKEND_HALIDE, DNN_BACKEND_INFERENCE_ENGINE)
CV_ENUM(DNNTarget, DNN_TARGET_CPU, DNN_TARGET_OPENCL)
static testing::internal::ParamGenerator<DNNTarget> availableDnnTargets()
{
static std::vector<DNNTarget> targets;
if (targets.empty())
{
targets.push_back(DNN_TARGET_CPU);
#ifdef HAVE_OPENCL
if (cv::ocl::useOpenCL())
targets.push_back(DNN_TARGET_OPENCL);
#endif
}
return testing::ValuesIn(targets);
}
}
#endif

263
modules/dnn/test/test_tf_importer.cpp
Unescape View File

@ -11,8 +11,6 @@ Test for Tensorflow models loading
#include "test_precomp.hpp"
#include "npy_blob.hpp"
#include <opencv2/core/ocl.hpp>
#include <opencv2/ts/ocl_test.hpp>
namespace opencv_test
{
@ -115,118 +113,85 @@ static void runTensorFlowNet(const std::string& prefix, int targetId = DNN_TARGE
normAssert(target, output, "", l1, lInf);
}
TEST(Test_TensorFlow, conv)
{
runTensorFlowNet("single_conv");
runTensorFlowNet("atrous_conv2d_valid");
runTensorFlowNet("atrous_conv2d_same");
runTensorFlowNet("depthwise_conv2d");
}
typedef testing::TestWithParam<DNNTarget> Test_TensorFlow_layers;
TEST(Test_TensorFlow, padding)
TEST_P(Test_TensorFlow_layers, conv)
{
runTensorFlowNet("padding_same");
runTensorFlowNet("padding_valid");
runTensorFlowNet("spatial_padding");
int targetId = GetParam();
runTensorFlowNet("single_conv", targetId);
runTensorFlowNet("atrous_conv2d_valid", targetId);
runTensorFlowNet("atrous_conv2d_same", targetId);
runTensorFlowNet("depthwise_conv2d", targetId);
}
TEST(Test_TensorFlow, eltwise_add_mul)
TEST_P(Test_TensorFlow_layers, padding)
{
runTensorFlowNet("eltwise_add_mul");
int targetId = GetParam();
runTensorFlowNet("padding_same", targetId);
runTensorFlowNet("padding_valid", targetId);
runTensorFlowNet("spatial_padding", targetId);
}
OCL_TEST(Test_TensorFlow, eltwise_add_mul)
TEST_P(Test_TensorFlow_layers, eltwise_add_mul)
{
runTensorFlowNet("eltwise_add_mul", DNN_TARGET_OPENCL);
runTensorFlowNet("eltwise_add_mul", GetParam());
}
TEST(Test_TensorFlow, pad_and_concat)
TEST_P(Test_TensorFlow_layers, pad_and_concat)
{
runTensorFlowNet("pad_and_concat");
runTensorFlowNet("pad_and_concat", GetParam());
}
TEST(Test_TensorFlow, batch_norm)
TEST_P(Test_TensorFlow_layers, batch_norm)
{
runTensorFlowNet("batch_norm");
runTensorFlowNet("fused_batch_norm");
runTensorFlowNet("batch_norm_text", DNN_TARGET_CPU, true);
runTensorFlowNet("mvn_batch_norm");
runTensorFlowNet("mvn_batch_norm_1x1");
int targetId = GetParam();
runTensorFlowNet("batch_norm", targetId);
runTensorFlowNet("fused_batch_norm", targetId);
runTensorFlowNet("batch_norm_text", targetId, true);
runTensorFlowNet("mvn_batch_norm", targetId);
runTensorFlowNet("mvn_batch_norm_1x1", targetId);
}
OCL_TEST(Test_TensorFlow, batch_norm)
TEST_P(Test_TensorFlow_layers, pooling)
{
runTensorFlowNet("batch_norm", DNN_TARGET_OPENCL);
runTensorFlowNet("fused_batch_norm", DNN_TARGET_OPENCL);
runTensorFlowNet("batch_norm_text", DNN_TARGET_OPENCL, true);
int targetId = GetParam();
runTensorFlowNet("max_pool_even", targetId);
runTensorFlowNet("max_pool_odd_valid", targetId);
runTensorFlowNet("ave_pool_same", targetId);
runTensorFlowNet("max_pool_odd_same", targetId);
}
TEST(Test_TensorFlow, pooling)
TEST_P(Test_TensorFlow_layers, deconvolution)
{
runTensorFlowNet("max_pool_even");
runTensorFlowNet("max_pool_odd_valid");
runTensorFlowNet("max_pool_odd_same");
runTensorFlowNet("ave_pool_same");
int targetId = GetParam();
runTensorFlowNet("deconvolution", targetId);
runTensorFlowNet("deconvolution_same", targetId);
runTensorFlowNet("deconvolution_stride_2_same", targetId);
runTensorFlowNet("deconvolution_adj_pad_valid", targetId);
runTensorFlowNet("deconvolution_adj_pad_same", targetId);
}
TEST(Test_TensorFlow, deconvolution)
TEST_P(Test_TensorFlow_layers, matmul)
{
runTensorFlowNet("deconvolution");
runTensorFlowNet("deconvolution_same");
runTensorFlowNet("deconvolution_stride_2_same");
runTensorFlowNet("deconvolution_adj_pad_valid");
runTensorFlowNet("deconvolution_adj_pad_same");
int targetId = GetParam();
runTensorFlowNet("matmul", targetId);
runTensorFlowNet("nhwc_reshape_matmul", targetId);
runTensorFlowNet("nhwc_transpose_reshape_matmul", targetId);
}
OCL_TEST(Test_TensorFlow, deconvolution)
TEST_P(Test_TensorFlow_layers, reshape)
{
runTensorFlowNet("deconvolution", DNN_TARGET_OPENCL);
runTensorFlowNet("deconvolution_same", DNN_TARGET_OPENCL);
runTensorFlowNet("deconvolution_stride_2_same", DNN_TARGET_OPENCL);
runTensorFlowNet("deconvolution_adj_pad_valid", DNN_TARGET_OPENCL);
runTensorFlowNet("deconvolution_adj_pad_same", DNN_TARGET_OPENCL);
int targetId = GetParam();
runTensorFlowNet("shift_reshape_no_reorder", targetId);
runTensorFlowNet("reshape_reduce", targetId);
runTensorFlowNet("flatten", targetId, true);
}
TEST(Test_TensorFlow, matmul)
{
runTensorFlowNet("matmul");
runTensorFlowNet("nhwc_reshape_matmul");
runTensorFlowNet("nhwc_transpose_reshape_matmul");
}
INSTANTIATE_TEST_CASE_P(/**/, Test_TensorFlow_layers, availableDnnTargets());
TEST(Test_TensorFlow, defun)
{
runTensorFlowNet("defun_dropout");
}
typedef testing::TestWithParam<DNNTarget> Test_TensorFlow_nets;
TEST(Test_TensorFlow, reshape)
{
runTensorFlowNet("shift_reshape_no_reorder");
runTensorFlowNet("reshape_reduce");
runTensorFlowNet("flatten", DNN_TARGET_CPU, true);
}
TEST(Test_TensorFlow, fp16)
{
const float l1 = 1e-3;
const float lInf = 1e-2;
runTensorFlowNet("fp16_single_conv", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_deconvolution", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_max_pool_odd_same", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_padding_valid", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_eltwise_add_mul", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_max_pool_odd_valid", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_pad_and_concat", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_max_pool_even", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_padding_same", DNN_TARGET_CPU, false, l1, lInf);
}
TEST(Test_TensorFlow, quantized)
{
runTensorFlowNet("uint8_single_conv");
}
TEST(Test_TensorFlow, MobileNet_SSD)
TEST_P(Test_TensorFlow_nets, MobileNet_SSD)
{
std::string netPath = findDataFile("dnn/ssd_mobilenet_v1_coco.pb", false);
std::string netConfig = findDataFile("dnn/ssd_mobilenet_v1_coco.pbtxt", false);
@ -249,17 +214,20 @@ TEST(Test_TensorFlow, MobileNet_SSD)
}
Net net = readNetFromTensorflow(netPath, netConfig);
net.setPreferableTarget(GetParam());
net.setInput(inp);
std::vector<Mat> output;
net.forward(output, outNames);
normAssert(target[0].reshape(1, 1), output[0].reshape(1, 1));
normAssert(target[0].reshape(1, 1), output[0].reshape(1, 1), "", 1e-5, 1.5e-4);
normAssert(target[1].reshape(1, 1), output[1].reshape(1, 1), "", 1e-5, 3e-4);
normAssert(target[2].reshape(1, 1), output[2].reshape(1, 1), "", 4e-5, 1e-2);
}
TEST(Test_TensorFlow, Inception_v2_SSD)
TEST_P(Test_TensorFlow_nets, Inception_v2_SSD)
{
std::string proto = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pbtxt", false);
std::string model = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pb", false);
@ -268,6 +236,8 @@ TEST(Test_TensorFlow, Inception_v2_SSD)
Mat img = imread(findDataFile("dnn/street.png", false));
Mat blob = blobFromImage(img, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), true, false);
net.setPreferableTarget(GetParam());
net.setInput(blob);
// Output has shape 1x1xNx7 where N - number of detections.
// An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]
@ -289,74 +259,57 @@ TEST(Test_TensorFlow, Inception_v2_SSD)
normAssert(detections, ref);
}
OCL_TEST(Test_TensorFlow, MobileNet_SSD)
{
std::string netPath = findDataFile("dnn/ssd_mobilenet_v1_coco.pb", false);
std::string netConfig = findDataFile("dnn/ssd_mobilenet_v1_coco.pbtxt", false);
std::string imgPath = findDataFile("dnn/street.png", false);
Mat inp;
resize(imread(imgPath), inp, Size(300, 300));
inp = blobFromImage(inp, 1.0f / 127.5, Size(), Scalar(127.5, 127.5, 127.5), true);
std::vector<String> outNames(3);
outNames[0] = "concat";
outNames[1] = "concat_1";
outNames[2] = "detection_out";
std::vector<Mat> target(outNames.size());
for (int i = 0; i < outNames.size(); ++i)
{
std::string path = findDataFile("dnn/tensorflow/ssd_mobilenet_v1_coco." + outNames[i] + ".npy", false);
target[i] = blobFromNPY(path);
}
Net net = readNetFromTensorflow(netPath, netConfig);
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
net.setInput(inp);
std::vector<Mat> output;
net.forward(output, outNames);
normAssert(target[0].reshape(1, 1), output[0].reshape(1, 1), "", 1e-5, 1.5e-4);
normAssert(target[1].reshape(1, 1), output[1].reshape(1, 1), "", 1e-5, 3e-4);
normAssert(target[2].reshape(1, 1), output[2].reshape(1, 1), "", 4e-5, 1e-2);
}
OCL_TEST(Test_TensorFlow, Inception_v2_SSD)
TEST_P(Test_TensorFlow_nets, opencv_face_detector_uint8)
{
std::string proto = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pbtxt", false);
std::string model = findDataFile("dnn/ssd_inception_v2_coco_2017_11_17.pb", false);
std::string proto = findDataFile("dnn/opencv_face_detector.pbtxt", false);
std::string model = findDataFile("dnn/opencv_face_detector_uint8.pb", false);
Net net = readNetFromTensorflow(model, proto);
Mat img = imread(findDataFile("dnn/street.png", false));
Mat blob = blobFromImage(img, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), true, false);
Mat img = imread(findDataFile("gpu/lbpcascade/er.png", false));
Mat blob = blobFromImage(img, 1.0, Size(), Scalar(104.0, 177.0, 123.0), false, false);
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
net.setPreferableTarget(GetParam());
net.setInput(blob);
// Output has shape 1x1xNx7 where N - number of detections.
// An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]
Mat out = net.forward();
out = out.reshape(1, out.total() / 7);
Mat detections;
for (int i = 0; i < out.rows; ++i)
{
if (out.at<float>(i, 2) > 0.5)
detections.push_back(out.row(i).colRange(1, 7));
}
// References are from test for Caffe model.
Mat ref = (Mat_<float>(6, 5) << 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631,
0.9934696, 0.2831718, 0.50738752, 0.345781, 0.5985168,
0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290,
0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477,
0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494,
0.95097077, 0.51901293, 0.45863652, 0.5777427, 0.5347801);
normAssert(out.reshape(1, out.total() / 7).rowRange(0, 6).colRange(2, 7), ref, "", 2.8e-4, 3.4e-3);
}
Mat ref = (Mat_<float>(5, 6) << 1, 0.90176028, 0.19872092, 0.36311883, 0.26461923, 0.63498729,
3, 0.93569964, 0.64865261, 0.45906419, 0.80675775, 0.65708131,
3, 0.75838411, 0.44668293, 0.45907149, 0.49459291, 0.52197015,
10, 0.95932811, 0.38349164, 0.32528657, 0.40387636, 0.39165527,
10, 0.93973452, 0.66561931, 0.37841269, 0.68074018, 0.42907384);
normAssert(detections, ref);
INSTANTIATE_TEST_CASE_P(/**/, Test_TensorFlow_nets, availableDnnTargets());
TEST(Test_TensorFlow, defun)
{
runTensorFlowNet("defun_dropout");
}
TEST(Test_TensorFlow, fp16)
{
const float l1 = 1e-3;
const float lInf = 1e-2;
runTensorFlowNet("fp16_single_conv", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_deconvolution", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_max_pool_odd_same", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_padding_valid", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_eltwise_add_mul", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_max_pool_odd_valid", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_pad_and_concat", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_max_pool_even", DNN_TARGET_CPU, false, l1, lInf);
runTensorFlowNet("fp16_padding_same", DNN_TARGET_CPU, false, l1, lInf);
}
TEST(Test_TensorFlow, quantized)
{
runTensorFlowNet("uint8_single_conv");
}
TEST(Test_TensorFlow, lstm)
@ -390,28 +343,4 @@ TEST(Test_TensorFlow, memory_read)
runTensorFlowNet("batch_norm_text", DNN_TARGET_CPU, true, l1, lInf, true);
}
TEST(Test_TensorFlow, opencv_face_detector_uint8)
{
std::string proto = findDataFile("dnn/opencv_face_detector.pbtxt", false);
std::string model = findDataFile("dnn/opencv_face_detector_uint8.pb", false);
Net net = readNetFromTensorflow(model, proto);
Mat img = imread(findDataFile("gpu/lbpcascade/er.png", false));
Mat blob = blobFromImage(img, 1.0, Size(), Scalar(104.0, 177.0, 123.0), false, false);
net.setInput(blob);
// Output has shape 1x1xNx7 where N - number of detections.
// An every detection is a vector of values [id, classId, confidence, left, top, right, bottom]
Mat out = net.forward();
// References are from test for Caffe model.
Mat ref = (Mat_<float>(6, 5) << 0.99520785, 0.80997437, 0.16379407, 0.87996572, 0.26685631,
0.9934696, 0.2831718, 0.50738752, 0.345781, 0.5985168,
0.99096733, 0.13629119, 0.24892329, 0.19756334, 0.3310290,
0.98977017, 0.23901358, 0.09084064, 0.29902688, 0.1769477,
0.97203469, 0.67965847, 0.06876482, 0.73999709, 0.1513494,
0.95097077, 0.51901293, 0.45863652, 0.5777427, 0.5347801);
normAssert(out.reshape(1, out.total() / 7).rowRange(0, 6).colRange(2, 7), ref, "", 2.8e-4, 3.4e-3);
}
}

251
modules/dnn/test/test_torch_importer.cpp
Unescape View File

@ -42,7 +42,6 @@
#include "test_precomp.hpp"
#include "npy_blob.hpp"
#include <opencv2/dnn/shape_utils.hpp>
#include <opencv2/ts/ocl_test.hpp>
namespace opencv_test
{
@ -100,219 +99,122 @@ static void runTorchNet(String prefix, int targetId = DNN_TARGET_CPU, String out
}
}
TEST(Torch_Importer, run_convolution)
{
runTorchNet("net_conv");
}
OCL_TEST(Torch_Importer, run_convolution)
{
runTorchNet("net_conv", DNN_TARGET_OPENCL);
}
TEST(Torch_Importer, run_pool_max)
{
runTorchNet("net_pool_max", DNN_TARGET_CPU, "", true);
}
OCL_TEST(Torch_Importer, run_pool_max)
{
runTorchNet("net_pool_max", DNN_TARGET_OPENCL, "", true);
}
TEST(Torch_Importer, run_pool_ave)
{
runTorchNet("net_pool_ave");
}
typedef testing::TestWithParam<DNNTarget> Test_Torch_layers;
OCL_TEST(Torch_Importer, run_pool_ave)
TEST_P(Test_Torch_layers, run_convolution)
{
runTorchNet("net_pool_ave", DNN_TARGET_OPENCL);
runTorchNet("net_conv", GetParam());
}
TEST(Torch_Importer, run_reshape)
TEST_P(Test_Torch_layers, run_pool_max)
{
runTorchNet("net_reshape");
runTorchNet("net_reshape_batch");
runTorchNet("net_reshape_single_sample");
runTorchNet("net_reshape_channels", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_pool_max", GetParam(), "", true);
}
TEST(Torch_Importer, run_linear)
TEST_P(Test_Torch_layers, run_pool_ave)
{
runTorchNet("net_linear_2d");
runTorchNet("net_pool_ave", GetParam());
}
TEST(Torch_Importer, run_paralel)
{
runTorchNet("net_parallel", DNN_TARGET_CPU, "l5_torchMerge");
}
TEST(Torch_Importer, run_concat)
{
runTorchNet("net_concat", DNN_TARGET_CPU, "l5_torchMerge");
runTorchNet("net_depth_concat", DNN_TARGET_CPU, "", false, true);
}
OCL_TEST(Torch_Importer, run_concat)
{
runTorchNet("net_concat", DNN_TARGET_OPENCL, "l5_torchMerge");
runTorchNet("net_depth_concat", DNN_TARGET_OPENCL, "", false, true);
}
TEST(Torch_Importer, run_deconv)
TEST_P(Test_Torch_layers, run_reshape)
{
runTorchNet("net_deconv");
int targetId = GetParam();
runTorchNet("net_reshape", targetId);
runTorchNet("net_reshape_batch", targetId);
runTorchNet("net_reshape_single_sample", targetId);
runTorchNet("net_reshape_channels", targetId, "", false, true);
}
OCL_TEST(Torch_Importer, run_deconv)
TEST_P(Test_Torch_layers, run_linear)
{
runTorchNet("net_deconv", DNN_TARGET_OPENCL);
runTorchNet("net_linear_2d", GetParam());
}
TEST(Torch_Importer, run_batch_norm)
TEST_P(Test_Torch_layers, run_concat)
{
runTorchNet("net_batch_norm", DNN_TARGET_CPU, "", false, true);
int targetId = GetParam();
runTorchNet("net_concat", targetId, "l5_torchMerge");
runTorchNet("net_depth_concat", targetId, "", false, true);
}
OCL_TEST(Torch_Importer, run_batch_norm)
TEST_P(Test_Torch_layers, run_deconv)
{
runTorchNet("net_batch_norm", DNN_TARGET_OPENCL, "", false, true);
runTorchNet("net_deconv", GetParam());
}
TEST(Torch_Importer, net_prelu)
TEST_P(Test_Torch_layers, run_batch_norm)
{
runTorchNet("net_prelu");
runTorchNet("net_batch_norm", GetParam(), "", false, true);
}
TEST(Torch_Importer, net_cadd_table)
TEST_P(Test_Torch_layers, net_prelu)
{
runTorchNet("net_cadd_table");
runTorchNet("net_prelu", GetParam());
}
TEST(Torch_Importer, net_softmax)
TEST_P(Test_Torch_layers, net_cadd_table)
{
runTorchNet("net_softmax");
runTorchNet("net_softmax_spatial");
runTorchNet("net_cadd_table", GetParam());
}
OCL_TEST(Torch_Importer, net_softmax)
TEST_P(Test_Torch_layers, net_softmax)
{
runTorchNet("net_softmax", DNN_TARGET_OPENCL);
runTorchNet("net_softmax_spatial", DNN_TARGET_OPENCL);
int targetId = GetParam();
runTorchNet("net_softmax", targetId);
runTorchNet("net_softmax_spatial", targetId);
}
TEST(Torch_Importer, net_logsoftmax)
TEST_P(Test_Torch_layers, net_logsoftmax)
{
runTorchNet("net_logsoftmax");
runTorchNet("net_logsoftmax_spatial");
}
OCL_TEST(Torch_Importer, net_logsoftmax)
{
runTorchNet("net_logsoftmax", DNN_TARGET_OPENCL);
runTorchNet("net_logsoftmax_spatial", DNN_TARGET_OPENCL);
}
TEST(Torch_Importer, net_lp_pooling)
TEST_P(Test_Torch_layers, net_lp_pooling)
{
runTorchNet("net_lp_pooling_square", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_lp_pooling_power", DNN_TARGET_CPU, "", false, true);
int targetId = GetParam();
runTorchNet("net_lp_pooling_square", targetId, "", false, true);
runTorchNet("net_lp_pooling_power", targetId, "", false, true);
}
TEST(Torch_Importer, net_conv_gemm_lrn)
TEST_P(Test_Torch_layers, net_conv_gemm_lrn)
{
runTorchNet("net_conv_gemm_lrn", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_conv_gemm_lrn", GetParam(), "", false, true);
}
TEST(Torch_Importer, net_inception_block)
TEST_P(Test_Torch_layers, net_inception_block)
{
runTorchNet("net_inception_block", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_inception_block", GetParam(), "", false, true);
}
TEST(Torch_Importer, net_normalize)
TEST_P(Test_Torch_layers, net_normalize)
{
runTorchNet("net_normalize", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_normalize", GetParam(), "", false, true);
}
OCL_TEST(Torch_Importer, net_normalize)
TEST_P(Test_Torch_layers, net_padding)
{
runTorchNet("net_normalize", DNN_TARGET_OPENCL, "", false, true);
int targetId = GetParam();
runTorchNet("net_padding", targetId, "", false, true);
runTorchNet("net_spatial_zero_padding", targetId, "", false, true);
runTorchNet("net_spatial_reflection_padding", targetId, "", false, true);
}
TEST(Torch_Importer, net_padding)
TEST_P(Test_Torch_layers, net_non_spatial)
{
runTorchNet("net_padding", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_spatial_zero_padding", DNN_TARGET_CPU, "", false, true);
runTorchNet("net_spatial_reflection_padding", DNN_TARGET_CPU, "", false, true);
}
TEST(Torch_Importer, net_non_spatial)
{
runTorchNet("net_non_spatial", DNN_TARGET_CPU, "", false, true);
}
OCL_TEST(Torch_Importer, net_non_spatial)
{
runTorchNet("net_non_spatial", DNN_TARGET_OPENCL, "", false, true);
}
TEST(Torch_Importer, ENet_accuracy)
{
Net net;
{
const string model = findDataFile("dnn/Enet-model-best.net", false);
net = readNetFromTorch(model, true);
ASSERT_FALSE(net.empty());
}
Mat sample = imread(_tf("street.png", false));
Mat inputBlob = blobFromImage(sample, 1./255);
net.setInput(inputBlob, "");
Mat out = net.forward();
Mat ref = blobFromNPY(_tf("torch_enet_prob.npy", false));
// Due to numerical instability in Pooling-Unpooling layers (indexes jittering)
// thresholds for ENet must be changed. Accuracy of resuults was checked on
// Cityscapes dataset and difference in mIOU with Torch is 10E-4%
normAssert(ref, out, "", 0.00044, 0.44);
const int N = 3;
for (int i = 0; i < N; i++)
{
net.setInput(inputBlob, "");
Mat out = net.forward();
normAssert(ref, out, "", 0.00044, 0.44);
}
runTorchNet("net_non_spatial", GetParam(), "", false, true);
}
TEST(Torch_Importer, OpenFace_accuracy)
{
const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false);
Net net = readNetFromTorch(model);
Mat sample = imread(findDataFile("cv/shared/lena.png", false));
Mat sampleF32(sample.size(), CV_32FC3);
sample.convertTo(sampleF32, sampleF32.type());
sampleF32 /= 255;
resize(sampleF32, sampleF32, Size(96, 96), 0, 0, INTER_NEAREST);
Mat inputBlob = blobFromImage(sampleF32);
INSTANTIATE_TEST_CASE_P(/**/, Test_Torch_layers, availableDnnTargets());
net.setInput(inputBlob);
Mat out = net.forward();
Mat outRef = readTorchBlob(_tf("net_openface_output.dat"), true);
normAssert(out, outRef);
}
typedef testing::TestWithParam<DNNTarget> Test_Torch_nets;
OCL_TEST(Torch_Importer, OpenFace_accuracy)
TEST_P(Test_Torch_nets, OpenFace_accuracy)
{
const string model = findDataFile("dnn/openface_nn4.small2.v1.t7", false);
Net net = readNetFromTorch(model);
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
net.setPreferableTarget(GetParam());
Mat sample = imread(findDataFile("cv/shared/lena.png", false));
Mat sampleF32(sample.size(), CV_32FC3);
@ -329,7 +231,7 @@ OCL_TEST(Torch_Importer, OpenFace_accuracy)
normAssert(out, outRef);
}
OCL_TEST(Torch_Importer, ENet_accuracy)
TEST_P(Test_Torch_nets, ENet_accuracy)
{
Net net;
{
@ -338,8 +240,7 @@ OCL_TEST(Torch_Importer, ENet_accuracy)
ASSERT_TRUE(!net.empty());
}
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
net.setPreferableTarget(GetParam());
Mat sample = imread(_tf("street.png", false));
Mat inputBlob = blobFromImage(sample, 1./255);
@ -374,7 +275,7 @@ OCL_TEST(Torch_Importer, ENet_accuracy)
// -median_filter 0 \
// -image_size 0 \
// -model models/instance_norm/feathers.t7
TEST(Torch_Importer, FastNeuralStyle_accuracy)
TEST_P(Test_Torch_nets, FastNeuralStyle_accuracy)
{
std::string models[] = {"dnn/fast_neural_style_eccv16_starry_night.t7",
"dnn/fast_neural_style_instance_norm_feathers.t7"};
@ -385,6 +286,8 @@ TEST(Torch_Importer, FastNeuralStyle_accuracy)
const string model = findDataFile(models[i], false);
Net net = readNetFromTorch(model);
net.setPreferableTarget(GetParam());
Mat img = imread(findDataFile("dnn/googlenet_1.png", false));
Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(103.939, 116.779, 123.68), false);
@ -404,37 +307,17 @@ TEST(Torch_Importer, FastNeuralStyle_accuracy)
}
}
OCL_TEST(Torch_Importer, FastNeuralStyle_accuracy)
{
std::string models[] = {"dnn/fast_neural_style_eccv16_starry_night.t7",
"dnn/fast_neural_style_instance_norm_feathers.t7"};
std::string targets[] = {"dnn/lena_starry_night.png", "dnn/lena_feathers.png"};
for (int i = 0; i < 2; ++i)
{
const string model = findDataFile(models[i], false);
Net net = readNetFromTorch(model);
net.setPreferableBackend(DNN_BACKEND_DEFAULT);
net.setPreferableTarget(DNN_TARGET_OPENCL);
Mat img = imread(findDataFile("dnn/googlenet_1.png", false));
Mat inputBlob = blobFromImage(img, 1.0, Size(), Scalar(103.939, 116.779, 123.68), false);
net.setInput(inputBlob);
Mat out = net.forward();
// Deprocessing.
getPlane(out, 0, 0) += 103.939;
getPlane(out, 0, 1) += 116.779;
getPlane(out, 0, 2) += 123.68;
out = cv::min(cv::max(0, out), 255);
INSTANTIATE_TEST_CASE_P(/**/, Test_Torch_nets, availableDnnTargets());
Mat ref = imread(findDataFile(targets[i]));
Mat refBlob = blobFromImage(ref, 1.0, Size(), Scalar(), false);
// TODO: fix OpenCL and add to the rest of tests
TEST(Torch_Importer, run_paralel)
{
runTorchNet("net_parallel", DNN_TARGET_CPU, "l5_torchMerge");
}
normAssert(out, refBlob, "", 0.5, 1.1);
}
TEST(Torch_Importer, DISABLED_run_paralel)
{
runTorchNet("net_parallel", DNN_TARGET_OPENCL, "l5_torchMerge");
}
}

Write Preview
Loading…
Cancel
Save