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

Merge pull request #11728 from dkurt:dnn_update_tf_ssd

Browse Source
pull/11732/head
Alexander Alekhin 7 years ago
parent f72633b9f5 40765c5f8d
commit 929d39f69a
4 changed files with 76 additions and 45 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. 20
      modules/dnn/perf/perf_net.cpp
  2. 39
      modules/dnn/test/test_backends.cpp
  3. 1
      modules/dnn/test/test_layers.cpp
  4. 61
      samples/dnn/tf_text_graph_ssd.py

20
modules/dnn/perf/perf_net.cpp
Unescape View File

@ -158,13 +158,19 @@ PERF_TEST_P_(DNNTestNetwork, MobileNet_SSD_Caffe)
Mat(cv::Size(300, 300), CV_32FC3));
}
// TODO: update MobileNet model.
PERF_TEST_P_(DNNTestNetwork, MobileNet_SSD_TensorFlow)
PERF_TEST_P_(DNNTestNetwork, MobileNet_SSD_v1_TensorFlow)
{
if (backend == DNN_BACKEND_HALIDE ||
backend == DNN_BACKEND_INFERENCE_ENGINE)
if (backend == DNN_BACKEND_HALIDE)
throw SkipTestException("");
processNet("dnn/ssd_mobilenet_v1_coco_2017_11_17.pb", "ssd_mobilenet_v1_coco_2017_11_17.pbtxt", "",
Mat(cv::Size(300, 300), CV_32FC3));
}
PERF_TEST_P_(DNNTestNetwork, MobileNet_SSD_v2_TensorFlow)
{
if (backend == DNN_BACKEND_HALIDE)
throw SkipTestException("");
processNet("dnn/ssd_mobilenet_v1_coco.pb", "ssd_mobilenet_v1_coco.pbtxt", "",
processNet("dnn/ssd_mobilenet_v2_coco_2018_03_29.pb", "ssd_mobilenet_v2_coco_2018_03_29.pbtxt", "",
Mat(cv::Size(300, 300), CV_32FC3));
}
@ -217,9 +223,7 @@ PERF_TEST_P_(DNNTestNetwork, opencv_face_detector)
PERF_TEST_P_(DNNTestNetwork, Inception_v2_SSD_TensorFlow)
{
if (backend == DNN_BACKEND_HALIDE ||
(backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_OPENCL) ||
(backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_OPENCL_FP16))
if (backend == DNN_BACKEND_HALIDE)
throw SkipTestException("");
processNet("dnn/ssd_inception_v2_coco_2017_11_17.pb", "ssd_inception_v2_coco_2017_11_17.pbtxt", "",
Mat(cv::Size(300, 300), CV_32FC3));

39
modules/dnn/test/test_backends.cpp
Unescape View File

@ -38,7 +38,7 @@ public:
void processNet(std::string weights, std::string proto,
Mat inp, const std::string& outputLayer = "",
std::string halideScheduler = "",
double l1 = 0.0, double lInf = 0.0)
double l1 = 0.0, double lInf = 0.0, double detectionConfThresh = 0.2)
{
if (backend == DNN_BACKEND_OPENCV && (target == DNN_TARGET_OPENCL || target == DNN_TARGET_OPENCL_FP16))
{
@ -87,7 +87,7 @@ public:
}
Mat out = net.forward(outputLayer).clone();
check(outDefault, out, outputLayer, l1, lInf, "First run");
check(outDefault, out, outputLayer, l1, lInf, detectionConfThresh, "First run");
// Test 2: change input.
float* inpData = (float*)inp.data;
@ -101,10 +101,11 @@ public:
net.setInput(inp);
outDefault = netDefault.forward(outputLayer).clone();
out = net.forward(outputLayer).clone();
check(outDefault, out, outputLayer, l1, lInf, "Second run");
check(outDefault, out, outputLayer, l1, lInf, detectionConfThresh, "Second run");
}
void check(Mat& ref, Mat& out, const std::string& outputLayer, double l1, double lInf, const char* msg)
void check(Mat& ref, Mat& out, const std::string& outputLayer, double l1, double lInf,
double detectionConfThresh, const char* msg)
{
if (outputLayer == "detection_out")
{
@ -119,7 +120,7 @@ public:
}
out = out.rowRange(0, numDetections);
}
normAssertDetections(ref, out, msg, 0.2, l1, lInf);
normAssertDetections(ref, out, msg, detectionConfThresh, l1, lInf);
}
else
normAssert(ref, out, msg, l1, lInf);
@ -188,20 +189,30 @@ TEST_P(DNNTestNetwork, MobileNet_SSD_Caffe)
inp, "detection_out", "", l1, lInf);
}
// TODO: update MobileNet model.
TEST_P(DNNTestNetwork, MobileNet_SSD_TensorFlow)
TEST_P(DNNTestNetwork, MobileNet_SSD_v1_TensorFlow)
{
if (backend == DNN_BACKEND_HALIDE ||
backend == DNN_BACKEND_INFERENCE_ENGINE)
if (backend == DNN_BACKEND_HALIDE)
throw SkipTestException("");
Mat sample = imread(findDataFile("dnn/street.png", false));
Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
float l1 = (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16) ? 0.008 : 0.0;
float lInf = (backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16) ? 0.06 : 0.0;
processNet("dnn/ssd_mobilenet_v1_coco.pb", "dnn/ssd_mobilenet_v1_coco.pbtxt",
float l1 = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.011 : 0.0;
float lInf = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.06 : 0.0;
processNet("dnn/ssd_mobilenet_v1_coco_2017_11_17.pb", "dnn/ssd_mobilenet_v1_coco_2017_11_17.pbtxt",
inp, "detection_out", "", l1, lInf);
}
TEST_P(DNNTestNetwork, MobileNet_SSD_v2_TensorFlow)
{
if (backend == DNN_BACKEND_HALIDE)
throw SkipTestException("");
Mat sample = imread(findDataFile("dnn/street.png", false));
Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);
float l1 = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.011 : 0.0;
float lInf = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.06 : 0.0;
processNet("dnn/ssd_mobilenet_v2_coco_2018_03_29.pb", "dnn/ssd_mobilenet_v2_coco_2018_03_29.pbtxt",
inp, "detection_out", "", l1, lInf, 0.25);
}
TEST_P(DNNTestNetwork, SSD_VGG16)
{
if (backend == DNN_BACKEND_HALIDE && target == DNN_TARGET_CPU)
@ -265,9 +276,7 @@ TEST_P(DNNTestNetwork, opencv_face_detector)
TEST_P(DNNTestNetwork, Inception_v2_SSD_TensorFlow)
{
if (backend == DNN_BACKEND_HALIDE ||
(backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_OPENCL) ||
(backend == DNN_BACKEND_INFERENCE_ENGINE && target == DNN_TARGET_OPENCL_FP16))
if (backend == DNN_BACKEND_HALIDE)
throw SkipTestException("");
Mat sample = imread(findDataFile("dnn/street.png", false));
Mat inp = blobFromImage(sample, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), false);

1
modules/dnn/test/test_layers.cpp
Unescape View File

@ -877,6 +877,7 @@ TEST_P(Layer_Test_DWconv_Prelu, Accuracy)
int shape[] = {1, num_input, 16, 16};
Mat in_blob(4, &shape[0], CV_32FC1, Scalar(1));
net.setPreferableBackend(DNN_BACKEND_OPENCV);
net.setInput(in_blob);
Mat out = net.forward();

61
samples/dnn/tf_text_graph_ssd.py
Unescape View File

@ -160,27 +160,40 @@ graph_def.node[1].input.append(weights)
# Create SSD postprocessing head ###############################################
# Concatenate predictions of classes, predictions of bounding boxes and proposals.
def tensorMsg(values):
if all([isinstance(v, float) for v in values]):
dtype = 'DT_FLOAT'
field = 'float_val'
elif all([isinstance(v, int) for v in values]):
dtype = 'DT_INT32'
field = 'int_val'
else:
raise Exception('Wrong values types')
concatAxis = NodeDef()
concatAxis.name = 'concat/axis_flatten'
concatAxis.op = 'Const'
text_format.Merge(
'tensor {'
' dtype: DT_INT32'
' tensor_shape { }'
' int_val: -1'
'}', concatAxis.attr["value"])
graph_def.node.extend([concatAxis])
def addConcatNode(name, inputs):
msg = 'tensor { dtype: ' + dtype + ' tensor_shape { dim { size: %d } }' % len(values)
for value in values:
msg += '%s: %s ' % (field, str(value))
return msg + '}'
def addConstNode(name, values):
node = NodeDef()
node.name = name
node.op = 'Const'
text_format.Merge(tensorMsg(values), node.attr["value"])
graph_def.node.extend([node])
def addConcatNode(name, inputs, axisNodeName):
concat = NodeDef()
concat.name = name
concat.op = 'ConcatV2'
for inp in inputs:
concat.input.append(inp)
concat.input.append(concatAxis.name)
concat.input.append(axisNodeName)
graph_def.node.extend([concat])
addConstNode('concat/axis_flatten', [-1])
addConstNode('PriorBox/concat/axis', [-2])
for label in ['ClassPredictor', 'BoxEncodingPredictor']:
concatInputs = []
for i in range(args.num_layers):
@ -193,19 +206,14 @@ for label in ['ClassPredictor', 'BoxEncodingPredictor']:
concatInputs.append(flatten.name)
graph_def.node.extend([flatten])
addConcatNode('%s/concat' % label, concatInputs)
addConcatNode('%s/concat' % label, concatInputs, 'concat/axis_flatten')
# Add layers that generate anchors (bounding boxes proposals).
scales = [args.min_scale + (args.max_scale - args.min_scale) * i / (args.num_layers - 1)
for i in range(args.num_layers)] + [1.0]
def tensorMsg(values):
msg = 'tensor { dtype: DT_FLOAT tensor_shape { dim { size: %d } }' % len(values)
for value in values:
msg += 'float_val: %f ' % value
return msg + '}'
priorBoxes = []
addConstNode('reshape_prior_boxes_to_4d', [1, 2, -1, 1])
for i in range(args.num_layers):
priorBox = NodeDef()
priorBox.name = 'PriorBox_%d' % i
@ -232,9 +240,18 @@ for i in range(args.num_layers):
text_format.Merge(tensorMsg([0.1, 0.1, 0.2, 0.2]), priorBox.attr["variance"])
graph_def.node.extend([priorBox])
priorBoxes.append(priorBox.name)
addConcatNode('PriorBox/concat', priorBoxes)
# Reshape from 1x2xN to 1x2xNx1
reshape = NodeDef()
reshape.name = priorBox.name + '/4d'
reshape.op = 'Reshape'
reshape.input.append(priorBox.name)
reshape.input.append('reshape_prior_boxes_to_4d')
graph_def.node.extend([reshape])
priorBoxes.append(reshape.name)
addConcatNode('PriorBox/concat', priorBoxes, 'PriorBox/concat/axis')
# Sigmoid for classes predictions and DetectionOutput layer
sigmoid = NodeDef()

Write Preview
Loading…
Cancel
Save