potok/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2026-07-30 07:43:03 +04:00
Code Packages Releases Wiki Activity

Merge pull request #12125 from dkurt:dnn_mobilenet_ppn

Browse Source
This commit is contained in:
Vadim Pisarevsky
2018-08-06 14:40:50 +00:00
parent 70b893333d 4fb086d6c3
commit 7c8ab271fc
3 changed files with 103 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/src/tensorflow/tf_importer.cpp
+55 -40
View File
@@ -716,6 +716,8 @@ void TFImporter::populateNet(Net dstNet)
// find all Const layers for params
std::map<String, int> value_id;
// A map with constant blobs which are shared between multiple layers.
std::map<String, Mat> sharedWeights;
addConstNodes(netBin, value_id, layers_to_ignore);
addConstNodes(netTxt, value_id, layers_to_ignore);
@@ -805,51 +807,64 @@ void TFImporter::populateNet(Net dstNet)
}
}
const tensorflow::TensorProto& kernelTensor = getConstBlob(layer, value_id);
kernelFromTensor(kernelTensor, layerParams.blobs[0]);
releaseTensor(const_cast<tensorflow::TensorProto*>(&kernelTensor));
int* kshape = layerParams.blobs[0].size.p;
const int outCh = kshape[0];
const int inCh = kshape[1];
const int height = kshape[2];
const int width = kshape[3];
if (type == "DepthwiseConv2dNative")
int kernelTensorInpId = -1;
const tensorflow::TensorProto& kernelTensor = getConstBlob(layer, value_id, -1, &kernelTensorInpId);
const String kernelTensorName = layer.input(kernelTensorInpId);
std::map<String, Mat>::iterator sharedWeightsIt = sharedWeights.find(kernelTensorName);
if (sharedWeightsIt == sharedWeights.end())
{
CV_Assert(!locPredTransposed);
const int chMultiplier = kshape[0];
kernelFromTensor(kernelTensor, layerParams.blobs[0]);
releaseTensor(const_cast<tensorflow::TensorProto*>(&kernelTensor));
Mat copy = layerParams.blobs[0].clone();
float* src = (float*)copy.data;
float* dst = (float*)layerParams.blobs[0].data;
for (int i = 0; i < chMultiplier; ++i)
for (int j = 0; j < inCh; ++j)
for (int s = 0; s < height * width; ++s)
{
int src_i = (i * inCh + j) * height * width + s;
int dst_i = (j * chMultiplier + i) * height* width + s;
dst[dst_i] = src[src_i];
}
// TODO Use reshape instead
kshape[0] = inCh * chMultiplier;
kshape[1] = 1;
size_t* kstep = layerParams.blobs[0].step.p;
kstep[0] = kstep[1]; // fix steps too
}
layerParams.set("kernel_h", height);
layerParams.set("kernel_w", width);
layerParams.set("num_output", outCh);
// Shuffle output channels from yxYX to xyXY.
if (locPredTransposed)
{
const int slice = height * width * inCh;
for (int i = 0; i < outCh; i += 2)
int* kshape = layerParams.blobs[0].size.p;
const int outCh = kshape[0];
const int inCh = kshape[1];
const int height = kshape[2];
const int width = kshape[3];
if (type == "DepthwiseConv2dNative")
{
cv::Mat src(1, slice, CV_32F, layerParams.blobs[0].ptr<float>(i));
cv::Mat dst(1, slice, CV_32F, layerParams.blobs[0].ptr<float>(i + 1));
std::swap_ranges(src.begin<float>(), src.end<float>(), dst.begin<float>());
CV_Assert(!locPredTransposed);
const int chMultiplier = kshape[0];
Mat copy = layerParams.blobs[0].clone();
float* src = (float*)copy.data;
float* dst = (float*)layerParams.blobs[0].data;
for (int i = 0; i < chMultiplier; ++i)
for (int j = 0; j < inCh; ++j)
for (int s = 0; s < height * width; ++s)
{
int src_i = (i * inCh + j) * height * width + s;
int dst_i = (j * chMultiplier + i) * height* width + s;
dst[dst_i] = src[src_i];
}
// TODO Use reshape instead
kshape[0] = inCh * chMultiplier;
kshape[1] = 1;
size_t* kstep = layerParams.blobs[0].step.p;
kstep[0] = kstep[1]; // fix steps too
}
// Shuffle output channels from yxYX to xyXY.
if (locPredTransposed)
{
const int slice = height * width * inCh;
for (int i = 0; i < outCh; i += 2)
{
cv::Mat src(1, slice, CV_32F, layerParams.blobs[0].ptr<float>(i));
cv::Mat dst(1, slice, CV_32F, layerParams.blobs[0].ptr<float>(i + 1));
std::swap_ranges(src.begin<float>(), src.end<float>(), dst.begin<float>());
}
}
sharedWeights[kernelTensorName] = layerParams.blobs[0];
}
else
{
layerParams.blobs[0] = sharedWeightsIt->second;
}
layerParams.set("kernel_h", layerParams.blobs[0].size[2]);
layerParams.set("kernel_w", layerParams.blobs[0].size[3]);
layerParams.set("num_output", layerParams.blobs[0].size[0]);
setStrides(layerParams, layer);
setPadding(layerParams, layer);
modules/dnn/test/test_tf_importer.cpp
+20
View File
@@ -337,6 +337,26 @@ TEST_P(Test_TensorFlow_nets, Inception_v2_Faster_RCNN)
normAssertDetections(ref, out, "", 0.3);
}
TEST_P(Test_TensorFlow_nets, MobileNet_v1_SSD_PPN)
{
checkBackend();
std::string proto = findDataFile("dnn/ssd_mobilenet_v1_ppn_coco.pbtxt", false);
std::string model = findDataFile("dnn/ssd_mobilenet_v1_ppn_coco.pb", false);
Net net = readNetFromTensorflow(model, proto);
Mat img = imread(findDataFile("dnn/dog416.png", false));
Mat ref = blobFromNPY(findDataFile("dnn/tensorflow/ssd_mobilenet_v1_ppn_coco.detection_out.npy", false));
Mat blob = blobFromImage(img, 1.0f / 127.5, Size(300, 300), Scalar(127.5, 127.5, 127.5), true, false);
net.setPreferableBackend(backend);
net.setPreferableTarget(target);
net.setInput(blob);
Mat out = net.forward();
double scoreDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.006 : default_l1;
normAssertDetections(ref, out, "", 0.4, scoreDiff, default_lInf);
}
TEST_P(Test_TensorFlow_nets, opencv_face_detector_uint8)
{
checkBackend();