mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-08-06 06:26:29 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Run entire SSDs from TensorFlow using Intel's Inference Engine

Browse Source
This commit is contained in:
Dmitry Kurtaev 2018-07-19 17:05:56 +03:00
parent 6c4f618db5
commit c213a3823e
3 changed files with 49 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

45
modules/dnn/src/tensorflow/tf_importer.cpp
View File

@ -771,6 +771,13 @@ void TFImporter::populateNet(Net dstNet)
type = layer.op();
}
// For the object detection networks, TensorFlow Object Detection API
// predicts deltas for bounding boxes in yxYX (ymin, xmin, ymax, xmax)
// order. We can manage it at DetectionOutput layer parsing predictions
// or shuffle last convolution's weights.
bool locPredTransposed = hasLayerAttr(layer, "loc_pred_transposed") &&
getLayerAttr(layer, "loc_pred_transposed").b();
layerParams.set("bias_term", false);
layerParams.blobs.resize(1);
@ -784,18 +791,32 @@ void TFImporter::populateNet(Net dstNet)
blobFromTensor(getConstBlob(net.node(weights_layer_index), value_id), layerParams.blobs[1]);
ExcludeLayer(net, weights_layer_index, 0, false);
layers_to_ignore.insert(next_layers[0].first);
// Shuffle bias from yxYX to xyXY.
if (locPredTransposed)
{
const int numWeights = layerParams.blobs[1].total();
float* biasData = reinterpret_cast<float*>(layerParams.blobs[1].data);
CV_Assert(numWeights % 4 == 0);
for (int i = 0; i < numWeights; i += 2)
{
std::swap(biasData[i], biasData[i + 1]);
}
}
}
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;
if (type == "DepthwiseConv2dNative")
{
const int chMultiplier = kshape[0];
const int outCh = kshape[0];
const int inCh = kshape[1];
const int height = kshape[2];
const int width = kshape[3];
if (type == "DepthwiseConv2dNative")
{
CV_Assert(!locPredTransposed);
const int chMultiplier = kshape[0];
Mat copy = layerParams.blobs[0].clone();
float* src = (float*)copy.data;
@ -814,9 +835,21 @@ void TFImporter::populateNet(Net dstNet)
size_t* kstep = layerParams.blobs[0].step.p;
kstep[0] = kstep[1]; // fix steps too
}
layerParams.set("kernel_h", kshape[2]);
layerParams.set("kernel_w", kshape[3]);
layerParams.set("num_output", kshape[0]);
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)
{
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>());
}
}
setStrides(layerParams, layer);
setPadding(layerParams, layer);

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

@ -309,7 +309,7 @@ TEST_P(Test_TensorFlow_nets, Inception_v2_SSD)
0, 10, 0.95932811, 0.38349164, 0.32528657, 0.40387636, 0.39165527,
0, 10, 0.93973452, 0.66561931, 0.37841269, 0.68074018, 0.42907384);
double scoreDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 5e-3 : default_l1;
double iouDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.025 : default_lInf;
double iouDiff = (target == DNN_TARGET_OPENCL_FP16 || target == DNN_TARGET_MYRIAD) ? 0.09 : default_lInf;
normAssertDetections(ref, out, "", 0.5, scoreDiff, iouDiff);
}

22
samples/dnn/tf_text_graph_ssd.py
View File

@ -208,12 +208,18 @@ for label in ['ClassPredictor', 'BoxEncodingPredictor']:
graph_def.node.extend([flatten])
addConcatNode('%s/concat' % label, concatInputs, 'concat/axis_flatten')
idx = 0
for node in graph_def.node:
if node.name == ('BoxPredictor_%d/BoxEncodingPredictor/Conv2D' % idx):
text_format.Merge('b: true', node.attr["loc_pred_transposed"])
idx += 1
assert(idx == args.num_layers)
# 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]
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
@ -240,18 +246,9 @@ 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)
# 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')
addConcatNode('PriorBox/concat', priorBoxes, 'concat/axis_flatten')
# Sigmoid for classes predictions and DetectionOutput layer
sigmoid = NodeDef()
@ -276,7 +273,6 @@ text_format.Merge('i: 100', detectionOut.attr['top_k'])
text_format.Merge('s: "CENTER_SIZE"', detectionOut.attr['code_type'])
text_format.Merge('i: 100', detectionOut.attr['keep_top_k'])
text_format.Merge('f: 0.01', detectionOut.attr['confidence_threshold'])
text_format.Merge('b: true', detectionOut.attr['loc_pred_transposed'])
graph_def.node.extend([detectionOut])