Chiebot-Mirror
/
opencv
8
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #13065 from dkurt:dnn_update_tf_faster_rcnn

Browse Source
pull/13193/head
Alexander Alekhin 6 years ago
parent 4b298a7460 dc9e6d3af8
commit 0c261acf3a
4 changed files with 63 additions and 49 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. 55
      modules/dnn/src/dnn.cpp
  2. 31
      modules/dnn/src/layers/pooling_layer.cpp
  3. 2
      modules/dnn/test/test_tf_importer.cpp
  4. 24
      samples/dnn/tf_text_graph_faster_rcnn.py

55
modules/dnn/src/dnn.cpp
Unescape View File

@ -1794,44 +1794,46 @@ struct Net::Impl
}
// fuse convolution layer followed by eltwise + relu
if ( IS_DNN_OPENCL_TARGET(preferableTarget) )
if ( IS_DNN_OPENCL_TARGET(preferableTarget) && ld.layerInstance->type == "Convolution" )
{
Ptr<EltwiseLayer> nextEltwiseLayer;
if( nextData )
nextEltwiseLayer = nextData->layerInstance.dynamicCast<EltwiseLayer>();
if( !nextEltwiseLayer.empty() && pinsToKeep.count(lpNext) == 0 )
if( !nextEltwiseLayer.empty() && pinsToKeep.count(lpNext) == 0 &&
nextData->inputBlobsId.size() == 2 )
{
LayerData *eltwiseData = nextData;
// go down from the second input and find the first non-skipped layer.
LayerData *downLayerData = &layers[eltwiseData->inputBlobsId[1].lid];
CV_Assert(downLayerData);
while (downLayerData->skip)
{
downLayerData = &layers[downLayerData->inputBlobsId[0].lid];
}
CV_Assert(downLayerData);
// second input layer is current layer.
if ( ld.id == downLayerData->id )
// Eltwise layer has two inputs. We need to determine which
// is a base convolution layer and which could be used as it's bias.
LayerData* biasLayerData = 0;
for (int i = 0; i < 2; ++i)
{
// go down from the first input and find the first non-skipped layer
downLayerData = &layers[eltwiseData->inputBlobsId[0].lid];
LayerData *downLayerData = &layers[eltwiseData->inputBlobsId[i].lid];
CV_Assert(downLayerData);
while (downLayerData->skip)
{
if ( !downLayerData->type.compare("Eltwise") )
downLayerData = &layers[downLayerData->inputBlobsId[1].lid];
else
if (downLayerData->inputBlobsId.size() == 1)
downLayerData = &layers[downLayerData->inputBlobsId[0].lid];
else
{
downLayerData = 0;
break;
}
}
Ptr<ConvolutionLayer> convLayer = downLayerData->layerInstance.dynamicCast<ConvolutionLayer>();
// first input layer is convolution layer
if( !convLayer.empty() && eltwiseData->consumers.size() == 1 )
if (downLayerData && ld.id == downLayerData->id)
{
biasLayerData = &layers[eltwiseData->inputBlobsId[1 - i].lid];
break;
}
}
CV_Assert(biasLayerData);
{
if( eltwiseData->consumers.size() == 1 )
{
// fuse eltwise + activation layer
LayerData *firstConvLayerData = downLayerData;
if (biasLayerData->id < ld.id)
{
nextData = &layers[eltwiseData->consumers[0].lid];
lpNext = LayerPin(eltwiseData->consumers[0].lid, 0);
@ -1845,8 +1847,8 @@ struct Net::Impl
!nextData->type.compare("Power")) &&
currLayer->setActivation(nextActivLayer) )
{
CV_Assert(firstConvLayerData->outputBlobsWrappers.size() == 1 && ld.inputBlobsWrappers.size() == 1);
ld.inputBlobsWrappers.push_back(firstConvLayerData->outputBlobsWrappers[0]);
CV_Assert_N(biasLayerData->outputBlobsWrappers.size() == 1, ld.inputBlobsWrappers.size() == 1);
ld.inputBlobsWrappers.push_back(biasLayerData->outputBlobsWrappers[0]);
printf_(("\tfused with %s\n", nextEltwiseLayer->name.c_str()));
printf_(("\tfused with %s\n", nextActivLayer->name.c_str()));
eltwiseData->skip = true;
@ -1897,9 +1899,6 @@ struct Net::Impl
}
}
if (preferableBackend != DNN_BACKEND_OPENCV)
continue; // Go to the next layer.
// the optimization #2. if there is no layer that takes max pooling layer's computed
// max indices (and only some semantical segmentation networks might need this;
// many others only take the maximum values), then we switch the max pooling

31
modules/dnn/src/layers/pooling_layer.cpp
Unescape View File

@ -95,7 +95,6 @@ public:
else if (params.has("pooled_w") || params.has("pooled_h"))
{
type = ROI;
computeMaxIdx = false;
pooledSize.width = params.get<uint32_t>("pooled_w", 1);
pooledSize.height = params.get<uint32_t>("pooled_h", 1);
}
@ -141,6 +140,7 @@ public:
#ifdef HAVE_OPENCL
poolOp.release();
#endif
computeMaxIdx = type == MAX;
}
virtual bool supportBackend(int backendId) CV_OVERRIDE
@ -190,19 +190,14 @@ public:
poolOp = Ptr<OCL4DNNPool<float> >(new OCL4DNNPool<float>(config));
}
for (size_t ii = 0; ii < inputs.size(); ii++)
{
UMat& inpMat = inputs[ii];
int out_index = (type == MAX) ? 2 : 1;
UMat& outMat = outputs[out_index * ii];
UMat maskMat = (type == MAX) ? outputs[2 * ii + 1] : UMat();
CV_Assert_N(inputs.size() == 1, !outputs.empty(), !computeMaxIdx || outputs.size() == 2);
UMat& inpMat = inputs[0];
UMat& outMat = outputs[0];
UMat maskMat = computeMaxIdx ? outputs[1] : UMat();
CV_Assert(inpMat.offset == 0 && outMat.offset == 0);
CV_Assert(inpMat.offset == 0 && outMat.offset == 0);
if (!poolOp->Forward(inpMat, outMat, maskMat))
return false;
}
return true;
return poolOp->Forward(inpMat, outMat, maskMat);
}
#endif
@ -229,9 +224,12 @@ public:
switch (type)
{
case MAX:
CV_Assert_N(inputs.size() == 1, outputs.size() == 2);
maxPooling(inputs[0], outputs[0], outputs[1]);
{
CV_Assert_N(inputs.size() == 1, !computeMaxIdx || outputs.size() == 2);
Mat mask = computeMaxIdx ? outputs[1] : Mat();
maxPooling(inputs[0], outputs[0], mask);
break;
}
case AVE:
CV_Assert_N(inputs.size() == 1, outputs.size() == 1);
avePooling(inputs[0], outputs[0]);
@ -912,7 +910,10 @@ public:
dims[0] = inputs[1][0]; // Number of proposals;
dims[1] = psRoiOutChannels;
}
outputs.assign(type == MAX ? 2 : 1, shape(dims, 4));
int numOutputs = requiredOutputs ? requiredOutputs : (type == MAX ? 2 : 1);
CV_Assert(numOutputs == 1 || (numOutputs == 2 && type == MAX));
outputs.assign(numOutputs, shape(dims, 4));
return false;
}

2
modules/dnn/test/test_tf_importer.cpp
Unescape View File

@ -358,7 +358,7 @@ TEST_P(Test_TensorFlow_nets, Faster_RCNN)
(backend == DNN_BACKEND_OPENCV && target == DNN_TARGET_OPENCL_FP16))
throw SkipTestException("");
for (int i = 1; i < 2; ++i)
for (int i = 0; i < 2; ++i)
{
std::string proto = findDataFile("dnn/" + names[i] + ".pbtxt", false);
std::string model = findDataFile("dnn/" + names[i] + ".pb", false);

24
samples/dnn/tf_text_graph_faster_rcnn.py
Unescape View File

@ -32,6 +32,8 @@ def createFasterRCNNGraph(modelPath, configPath, outputPath):
width_stride = float(grid_anchor_generator['width_stride'][0])
height_stride = float(grid_anchor_generator['height_stride'][0])
features_stride = float(config['feature_extractor'][0]['first_stage_features_stride'][0])
first_stage_nms_iou_threshold = float(config['first_stage_nms_iou_threshold'][0])
first_stage_max_proposals = int(config['first_stage_max_proposals'][0])
print('Number of classes: %d' % num_classes)
print('Scales: %s' % str(scales))
@ -47,7 +49,8 @@ def createFasterRCNNGraph(modelPath, configPath, outputPath):
removeIdentity(graph_def)
def to_remove(name, op):
return name.startswith(scopesToIgnore) or not name.startswith(scopesToKeep)
return name.startswith(scopesToIgnore) or not name.startswith(scopesToKeep) or \
(name.startswith('CropAndResize') and op != 'CropAndResize')
removeUnusedNodesAndAttrs(to_remove, graph_def)
@ -114,10 +117,10 @@ def createFasterRCNNGraph(modelPath, configPath, outputPath):
detectionOut.addAttr('num_classes', 2)
detectionOut.addAttr('share_location', True)
detectionOut.addAttr('background_label_id', 0)
detectionOut.addAttr('nms_threshold', 0.7)
detectionOut.addAttr('nms_threshold', first_stage_nms_iou_threshold)
detectionOut.addAttr('top_k', 6000)
detectionOut.addAttr('code_type', "CENTER_SIZE")
detectionOut.addAttr('keep_top_k', 100)
detectionOut.addAttr('keep_top_k', first_stage_max_proposals)
detectionOut.addAttr('clip', False)
graph_def.node.extend([detectionOut])
@ -147,9 +150,11 @@ def createFasterRCNNGraph(modelPath, configPath, outputPath):
'SecondStageBoxPredictor/Reshape_1/Reshape', [1, -1], graph_def)
# Replace Flatten subgraph onto a single node.
cropAndResizeNodeName = ''
for i in reversed(range(len(graph_def.node))):
if graph_def.node[i].op == 'CropAndResize':
graph_def.node[i].input.insert(1, 'detection_out/clip_by_value')
cropAndResizeNodeName = graph_def.node[i].name
if graph_def.node[i].name == 'SecondStageBoxPredictor/Reshape':
addConstNode('SecondStageBoxPredictor/Reshape/shape2', [1, -1, 4], graph_def)
@ -159,11 +164,15 @@ def createFasterRCNNGraph(modelPath, configPath, outputPath):
if graph_def.node[i].name in ['SecondStageBoxPredictor/Flatten/flatten/Shape',
'SecondStageBoxPredictor/Flatten/flatten/strided_slice',
'SecondStageBoxPredictor/Flatten/flatten/Reshape/shape']:
'SecondStageBoxPredictor/Flatten/flatten/Reshape/shape',
'SecondStageBoxPredictor/Flatten_1/flatten/Shape',
'SecondStageBoxPredictor/Flatten_1/flatten/strided_slice',
'SecondStageBoxPredictor/Flatten_1/flatten/Reshape/shape']:
del graph_def.node[i]
for node in graph_def.node:
if node.name == 'SecondStageBoxPredictor/Flatten/flatten/Reshape':
if node.name == 'SecondStageBoxPredictor/Flatten/flatten/Reshape' or \
node.name == 'SecondStageBoxPredictor/Flatten_1/flatten/Reshape':
node.op = 'Flatten'
node.input.pop()
@ -171,6 +180,11 @@ def createFasterRCNNGraph(modelPath, configPath, outputPath):
'SecondStageBoxPredictor/BoxEncodingPredictor/MatMul']:
node.addAttr('loc_pred_transposed', True)
if node.name.startswith('MaxPool2D'):
assert(node.op == 'MaxPool')
assert(cropAndResizeNodeName)
node.input = [cropAndResizeNodeName]
################################################################################
### Postprocessing
################################################################################

Write Preview
Loading…
Cancel
Save