mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2024-11-29 05:29:54 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Update a script to generate text graphs for Faster-RCNN networks from TensorFlow

Browse Source
This commit is contained in:
Dmitry Kurtaev 2018-11-07 11:16:15 +03:00
parent e75576e1ab
commit dc9e6d3af8
4 changed files with 63 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
modules/dnn/src/dnn.cpp
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];
if (downLayerData->inputBlobsId.size() == 1)
downLayerData = &layers[downLayerData->inputBlobsId[0].lid];
else
downLayerData = &layers[downLayerData->inputBlobsId[0].lid];
{
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

29
modules/dnn/src/layers/pooling_layer.cpp
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);
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
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
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
################################################################################