third_party/opencv
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #16223 from l-bat:lip_jppnet

Browse Source
This commit is contained in:
Alexander Alekhin
2020-01-27 19:17:43 +00:00
parent 02f8a9470a 24166ac402
commit 5429b1f5ff
9 changed files with 364 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/dnn/include/opencv2/dnn/all_layers.hpp
+2 -1
View File
@@ -250,7 +250,8 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
std::vector<size_t> pads_begin, pads_end;
CV_DEPRECATED_EXTERNAL Size kernel, stride, pad;
CV_DEPRECATED_EXTERNAL int pad_l, pad_t, pad_r, pad_b;
bool globalPooling;
bool globalPooling; //!< Flag is true if at least one of the axes is global pooled.
std::vector<bool> isGlobalPooling;
bool computeMaxIdx;
String padMode;
bool ceilMode;
modules/dnn/include/opencv2/dnn/dnn.hpp
+2 -2
View File
@@ -47,9 +47,9 @@
#include "opencv2/core/async.hpp"
#if !defined CV_DOXYGEN && !defined CV_STATIC_ANALYSIS && !defined CV_DNN_DONT_ADD_EXPERIMENTAL_NS
#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_34_v15 {
#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_34_v16 {
#define CV__DNN_EXPERIMENTAL_NS_END }
namespace cv { namespace dnn { namespace experimental_dnn_34_v15 { } using namespace experimental_dnn_34_v15; }}
namespace cv { namespace dnn { namespace experimental_dnn_34_v16 { } using namespace experimental_dnn_34_v16; }}
#else
#define CV__DNN_EXPERIMENTAL_NS_BEGIN
#define CV__DNN_EXPERIMENTAL_NS_END
modules/dnn/src/layers/layers_common.cpp
+21 -10
View File
@@ -144,26 +144,37 @@ void getStrideAndPadding(const LayerParams &params, std::vector<size_t>& pads_be
}
}
void getPoolingKernelParams(const LayerParams &params, std::vector<size_t>& kernel, bool &globalPooling,
void getPoolingKernelParams(const LayerParams &params, std::vector<size_t>& kernel, std::vector<bool>& globalPooling,
std::vector<size_t>& pads_begin, std::vector<size_t>& pads_end,
std::vector<size_t>& strides, cv::String &padMode)
{
globalPooling = params.has("global_pooling") &&
params.get<bool>("global_pooling");
bool is_global = params.get<bool>("global_pooling", false);
globalPooling.resize(3);
globalPooling[0] = params.get<bool>("global_pooling_d", is_global);
globalPooling[1] = params.get<bool>("global_pooling_h", is_global);
globalPooling[2] = params.get<bool>("global_pooling_w", is_global);
if (globalPooling)
if (globalPooling[0] || globalPooling[1] || globalPooling[2])
{
util::getStrideAndPadding(params, pads_begin, pads_end, strides, padMode);
if(params.has("kernel_h") || params.has("kernel_w") || params.has("kernel_size"))
{
if ((globalPooling[0] && params.has("kernel_d")) ||
(globalPooling[1] && params.has("kernel_h")) ||
(globalPooling[2] && params.has("kernel_w")) ||
params.has("kernel_size")) {
CV_Error(cv::Error::StsBadArg, "In global_pooling mode, kernel_size (or kernel_h and kernel_w) cannot be specified");
}
for (int i = 0; i < pads_begin.size(); i++) {
if (pads_begin[i] != 0 || pads_end[i] != 0)
kernel.resize(3);
kernel[0] = params.get<int>("kernel_d", 1);
kernel[1] = params.get<int>("kernel_h", 1);
kernel[2] = params.get<int>("kernel_w", 1);
for (int i = 0, j = globalPooling.size() - pads_begin.size(); i < pads_begin.size(); i++, j++) {
if ((pads_begin[i] != 0 || pads_end[i] != 0) && globalPooling[j])
CV_Error(cv::Error::StsBadArg, "In global_pooling mode, pads must be = 0");
}
for (int i = 0; i < strides.size(); i++) {
if (strides[i] != 1)
for (int i = 0, j = globalPooling.size() - strides.size(); i < strides.size(); i++, j++) {
if (strides[i] != 1 && globalPooling[j])
CV_Error(cv::Error::StsBadArg, "In global_pooling mode, strides must be = 1");
}
}
modules/dnn/src/layers/layers_common.hpp
+1 -1
View File
@@ -63,7 +63,7 @@ void getConvolutionKernelParams(const LayerParams &params, std::vector<size_t>&
std::vector<size_t>& pads_end, std::vector<size_t>& strides, std::vector<size_t>& dilations,
cv::String &padMode, std::vector<size_t>& adjust_pads);
void getPoolingKernelParams(const LayerParams &params, std::vector<size_t>& kernel, bool &globalPooling,
void getPoolingKernelParams(const LayerParams &params, std::vector<size_t>& kernel, std::vector<bool>& globalPooling,
std::vector<size_t>& pads_begin, std::vector<size_t>& pads_end, std::vector<size_t>& strides, cv::String &padMode);
void getConvPoolOutParams(const std::vector<int>& inp, const std::vector<size_t>& kernel,
modules/dnn/src/layers/pooling_layer.cpp
+24 -12
View File
@@ -79,6 +79,7 @@ public:
{
computeMaxIdx = true;
globalPooling = false;
isGlobalPooling = std::vector<bool>(3, false);
stride = Size(1, 1);
pad_t = pad_l = pad_b = pad_r = 0;
@@ -95,7 +96,8 @@ public:
else
CV_Error(Error::StsBadArg, "Unknown pooling type \"" + pool + "\"");
getPoolingKernelParams(params, kernel_size, globalPooling, pads_begin, pads_end, strides, padMode);
getPoolingKernelParams(params, kernel_size, isGlobalPooling, pads_begin, pads_end, strides, padMode);
globalPooling = isGlobalPooling[0] || isGlobalPooling[1] || isGlobalPooling[2];
if (kernel_size.size() == 2) {
kernel = Size(kernel_size[1], kernel_size[0]);
stride = Size(strides[1], strides[0]);
@@ -147,9 +149,14 @@ public:
out.push_back(outputs[0].size[i]);
}
if (globalPooling) {
kernel = Size(inp[1], inp[0]);
kernel_size = std::vector<size_t>(inp.begin(), inp.end());
}
std::vector<size_t> finalKernel;
for (int i = 0; i < inp.size(); i++) {
int idx = isGlobalPooling.size() - inp.size() + i;
finalKernel.push_back(isGlobalPooling[idx] ? inp[i] : kernel_size[idx]);
}
kernel_size = finalKernel;
kernel = Size(kernel_size[1], kernel_size[0]);
}
getConvPoolPaddings(inp, kernel_size, strides, padMode, pads_begin, pads_end);
if (pads_begin.size() == 2) {
@@ -995,20 +1002,25 @@ virtual Ptr<BackendNode> initNgraph(const std::vector<Ptr<BackendWrapper> >& inp
std::vector<int> inpShape(inputs[0].begin() + 2, inputs[0].end());
std::vector<int> outShape(inputs[0].begin(), inputs[0].begin() + 2);
if (globalPooling)
{
outShape.push_back(1);
outShape.push_back(1);
std::vector<size_t> local_kernel;
if (globalPooling) {
for (int i = 0; i < inpShape.size(); i++) {
int idx = isGlobalPooling.size() - inpShape.size() + i;
local_kernel.push_back(isGlobalPooling[idx] ? inpShape[i] : kernel_size[idx]);
}
} else {
local_kernel = kernel_size;
}
else if (type == ROI || type == PSROI)
if (type == ROI || type == PSROI)
{
outShape.push_back(pooledSize.height);
outShape.push_back(pooledSize.width);
}
else if (padMode.empty())
{
for (int i = 0; i < kernel_size.size(); i++) {
float dst = (float)(inpShape[i] + pads_begin[i] + pads_end[i] - kernel_size[i]) / strides[i];
for (int i = 0; i < local_kernel.size(); i++) {
float dst = (float)(inpShape[i] + pads_begin[i] + pads_end[i] - local_kernel[i]) / strides[i];
outShape.push_back(1 + (ceilMode ? ceil(dst) : floor(dst)));
}
@@ -1023,7 +1035,7 @@ virtual Ptr<BackendNode> initNgraph(const std::vector<Ptr<BackendWrapper> >& inp
}
else
{
getConvPoolOutParams(inpShape, kernel_size, strides, padMode, std::vector<size_t>(kernel_size.size(), 1), outShape);
getConvPoolOutParams(inpShape, local_kernel, strides, padMode, std::vector<size_t>(local_kernel.size(), 1), outShape);
}
if (type == ROI)
{
modules/dnn/src/layers/slice_layer.cpp
+2 -1
View File
@@ -114,7 +114,8 @@ public:
virtual bool supportBackend(int backendId) CV_OVERRIDE
{
return backendId == DNN_BACKEND_OPENCV ||
((backendId == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 || backendId == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH) &&
(backendId == DNN_BACKEND_INFERENCE_ENGINE_NGRAPH && sliceRanges.size() == 1) ||
(backendId == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019 &&
#ifdef HAVE_INF_ENGINE
INF_ENGINE_VER_MAJOR_GE(INF_ENGINE_RELEASE_2019R1) &&
#endif
modules/dnn/src/tensorflow/tf_importer.cpp
+127 -13
View File
@@ -1936,20 +1936,22 @@ void TFImporter::populateNet(Net dstNet)
}
else if (type == "Mean")
{
// Computes the mean of elements across dimensions of a tensor.
// If keepdims is false (default) reduces input_tensor along the dimensions given in axis,
// else the reduced dimensions are retained with length 1.
// if indices = [1, 2] in NHWC layout we use global pooling: NxCxHxW --Pooling--> NxCx1x1
// if keepdims is false we use Flatten after Pooling: out_shape = NxC
// if indices = [0] we use a global pooling by indices.
// To return correct shape, we use Reshape after Pooling. To determine input shape use Slice for input,
// if keepdims is false we use Flatten after Slice.
// Example: input_shape = NxCxHxW
// determine out shape: NxCxHxW --Slice--> 1xCxHxW
// out_shape = 1xCxHxW if keepDims else (1xCxHxW --Flatten--> CxHxW)
// global pool: NxCxHxW --Flatten--> Nx(C*H*W) --Reshape--> 1x1xNx(C*H*W) --Pooling--> 1x1x1x(C*H*W) --Reshape--> out_shape
Mat indices = getTensorContent(getConstBlob(layer, value_id, 1));
CV_Assert(indices.type() == CV_32SC1);
if (indices.total() != 2 || indices.at<int>(0) != 1 || indices.at<int>(1) != 2)
CV_Error(Error::StsNotImplemented, "Unsupported mode of reduce_mean operation.");
layerParams.set("pool", "ave");
layerParams.set("global_pooling", true);
int id = dstNet.addLayer(name, "Pooling", layerParams);
layer_id[name] = id;
connect(layer_id, dstNet, parsePin(layer.input(0)), id, 0);
// There are two attributes, "keepdims" and a deprecated "keep_dims".
bool keepDims = false;
if (hasLayerAttr(layer, "keepdims"))
@@ -1957,16 +1959,128 @@ void TFImporter::populateNet(Net dstNet)
else if (hasLayerAttr(layer, "keep_dims"))
keepDims = getLayerAttr(layer, "keep_dims").b();
if (!keepDims)
if (indices.total() == 1 && indices.at<int>(0) == 0)
{
LayerParams flattenLp;
std::string flattenName = name + "/flatten";
CV_Assert(layer_id.find(flattenName) == layer_id.end());
int flattenId = dstNet.addLayer(flattenName, "Flatten", flattenLp);
layer_id[flattenName] = flattenId;
connect(layer_id, dstNet, Pin(name), flattenId, 0);
connect(layer_id, dstNet, parsePin(layer.input(0)), flattenId, 0);
LayerParams reshapeLp;
std::string reshapeName = name + "/reshape";
CV_Assert(layer_id.find(reshapeName) == layer_id.end());
reshapeLp.set("axis", 0);
reshapeLp.set("num_axes", 1);
int newShape[] = {1, 1, -1};
reshapeLp.set("dim", DictValue::arrayInt(&newShape[0], 3));
int reshapeId = dstNet.addLayer(reshapeName, "Reshape", reshapeLp);
layer_id[reshapeName] = reshapeId;
connect(layer_id, dstNet, Pin(flattenName), reshapeId, 0);
LayerParams avgLp;
std::string avgName = name + "/avg";
CV_Assert(layer_id.find(avgName) == layer_id.end());
avgLp.set("pool", "ave");
// pooling kernel H x 1
avgLp.set("global_pooling_h", true);
avgLp.set("kernel_w", 1);
int avgId = dstNet.addLayer(avgName, "Pooling", avgLp);
layer_id[avgName] = avgId;
connect(layer_id, dstNet, Pin(reshapeName), avgId, 0);
LayerParams sliceLp;
std::string layerShapeName = name + "/slice";
CV_Assert(layer_id.find(layerShapeName) == layer_id.end());
sliceLp.set("axis", 0);
int begin[] = {0};
int size[] = {1};
sliceLp.set("begin", DictValue::arrayInt(&begin[0], 1));
sliceLp.set("size", DictValue::arrayInt(&size[0], 1));
int sliceId = dstNet.addLayer(layerShapeName, "Slice", sliceLp);
layer_id[layerShapeName] = sliceId;
connect(layer_id, dstNet, Pin(layer.input(0)), sliceId, 0);
if (!keepDims)
{
LayerParams squeezeLp;
std::string squeezeName = name + "/squeeze";
CV_Assert(layer_id.find(squeezeName) == layer_id.end());
squeezeLp.set("axis", 0);
squeezeLp.set("end_axis", 1);
int squeezeId = dstNet.addLayer(squeezeName, "Flatten", squeezeLp);
layer_id[squeezeName] = squeezeId;
connect(layer_id, dstNet, Pin(layerShapeName), squeezeId, 0);
layerShapeName = squeezeName;
}
int id = dstNet.addLayer(name, "Reshape", layerParams);
layer_id[name] = id;
connect(layer_id, dstNet, Pin(avgName), id, 0);
connect(layer_id, dstNet, Pin(layerShapeName), id, 1);
} else {
if (indices.total() != 2 || indices.at<int>(0) != 1 || indices.at<int>(1) != 2)
CV_Error(Error::StsNotImplemented, "Unsupported mode of reduce_mean operation.");
layerParams.set("pool", "ave");
layerParams.set("global_pooling", true);
int id = dstNet.addLayer(name, "Pooling", layerParams);
layer_id[name] = id;
connect(layer_id, dstNet, parsePin(layer.input(0)), id, 0);
if (!keepDims)
{
LayerParams flattenLp;
std::string flattenName = name + "/flatten";
CV_Assert(layer_id.find(flattenName) == layer_id.end());
int flattenId = dstNet.addLayer(flattenName, "Flatten", flattenLp);
layer_id[flattenName] = flattenId;
connect(layer_id, dstNet, Pin(name), flattenId, 0);
}
}
}
else if (type == "Pack")
{
// op: tf.stack(list of tensors, axis=0)
// Join a list of inputs along a new axis.
// The "axis" specifies the index of the new axis in the dimensions of the output.
// Example: given a list with "N" tensors of shape (C, H, W):
// if axis == 0 then the output tensor will have the shape (N, C, H, W),
// if axis == 1 then the output tensor will have the shape (C, N, H, W).
CV_Assert(hasLayerAttr(layer, "axis"));
int dim = (int)getLayerAttr(layer, "axis").i();
if (dim != 0)
CV_Error(Error::StsNotImplemented, "Unsupported mode of pack operation.");
CV_Assert(hasLayerAttr(layer, "N"));
int num = (int)getLayerAttr(layer, "N").i();
CV_Assert(layer.input_size() == num);
std::string base_name = name + "/reshape_";
std::vector<int> reshape_ids;
for (int i = 0; i < num; i++) {
std::ostringstream ss;
ss << i;
std::string reshape_name = base_name + ss.str();
LayerParams reshapeLP;
reshapeLP.set("axis", dim);
reshapeLP.set("num_axes", 1);
int outShape[] = {1, -1};
reshapeLP.set("dim", DictValue::arrayInt(&outShape[0], 2));
int id = dstNet.addLayer(reshape_name, "Reshape", reshapeLP);
layer_id[reshape_name] = id;
reshape_ids.push_back(id);
connect(layer_id, dstNet, parsePin(layer.input(i)), id, 0);
}
layerParams.set("axis", dim);
int id = dstNet.addLayer(name, "Concat", layerParams);
layer_id[name] = id;
for (int li = 0; li < num; li++)
dstNet.connect(reshape_ids[li], 0, id, li);
}
else if (type == "ClipByValue")
{
// op: "ClipByValue"
modules/dnn/test/test_tf_importer.cpp
+7
View File
@@ -121,6 +121,13 @@ public:
}
};
TEST_P(Test_TensorFlow_layers, reduce_mean)
{
if (backend == DNN_BACKEND_INFERENCE_ENGINE_NN_BUILDER_2019)
applyTestTag(CV_TEST_TAG_DNN_SKIP_IE_NN_BUILDER);
runTensorFlowNet("global_pool_by_axis");
}
TEST_P(Test_TensorFlow_layers, conv)
{
runTensorFlowNet("single_conv");