Skip to content

O
opencv
Commit 346871e2 authored by Dmitry Kurtaev's avatar Dmitry Kurtaev
Browse files
Options

Set output layers names and types for models in DLDT's intermediate representation

parent e4b51fa8
Hide whitespace changes
Inline Side-by-side
Showing with 81 additions and 49 deletions
modules/dnn/src/dnn.cpp
View file @ 346871e2
......@@ -1993,11 +1993,17 @@ Net Net::readFromModelOptimizer(const String& xml, const String& bin)
backendNode->net = Ptr<InfEngineBackendNet>(new InfEngineBackendNet(ieNet));
for (auto& it : ieNet.getOutputsInfo())
{
Ptr<Layer> cvLayer(new InfEngineBackendLayer(it.second));
InferenceEngine::CNNLayerPtr ieLayer = ieNet.getLayerByName(it.first.c_str());
CV_Assert(ieLayer);
LayerParams lp;
int lid = cvNet.addLayer(it.first, "", lp);
LayerData& ld = cvNet.impl->layers[lid];
ld.layerInstance = Ptr<Layer>(new InfEngineBackendLayer(it.second));
cvLayer->name = it.first;
cvLayer->type = ieLayer->type;
ld.layerInstance = cvLayer;
ld.backendNodes[DNN_BACKEND_INFERENCE_ENGINE] = backendNode;
for (int i = 0; i < inputsNames.size(); ++i)
......
modules/dnn/test/test_layers.cpp
View file @ 346871e2
......@@ -925,6 +925,10 @@ TEST(Layer_Test_Convolution_DLDT, Accuracy)
Mat out = net.forward();
normAssert(outDefault, out);
std::vector<int> outLayers = net.getUnconnectedOutLayers();
ASSERT_EQ(net.getLayer(outLayers[0])->name, "output_merge");
ASSERT_EQ(net.getLayer(outLayers[0])->type, "Concat");
}
// 1. Create a .prototxt file with the following network:
......
samples/dnn/object_detection.cpp
View file @ 346871e2
......@@ -22,6 +22,7 @@ const char* keys =
"{ height | -1 | Preprocess input image by resizing to a specific height. }"
"{ rgb | | Indicate that model works with RGB input images instead BGR ones. }"
"{ thr | .5 | Confidence threshold. }"
"{ thr | .4 | Non-maximum suppression threshold. }"
"{ backend | 0 | Choose one of computation backends: "
"0: automatically (by default), "
"1: Halide language (http://halide-lang.org/), "
......@@ -37,7 +38,7 @@ const char* keys =
using namespace cv;
using namespace dnn;
float confThreshold;
float confThreshold, nmsThreshold;
std::vector<std::string> classes;
void postprocess(Mat& frame, const std::vector<Mat>& out, Net& net);
......@@ -59,6 +60,7 @@ int main(int argc, char** argv)
}
confThreshold = parser.get<float>("thr");
nmsThreshold = parser.get<float>("nms");
float scale = parser.get<float>("scale");
Scalar mean = parser.get<Scalar>("mean");
bool swapRB = parser.get<bool>("rgb");
......@@ -144,6 +146,9 @@ void postprocess(Mat& frame, const std::vector<Mat>& outs, Net& net)
static std::vector<int> outLayers = net.getUnconnectedOutLayers();
static std::string outLayerType = net.getLayer(outLayers[0])->type;
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
if (net.getLayer(0)->outputNameToIndex("im_info") != -1) // Faster-RCNN or R-FCN
{
// Network produces output blob with a shape 1x1xNx7 where N is a number of
......@@ -160,8 +165,11 @@ void postprocess(Mat& frame, const std::vector<Mat>& outs, Net& net)
int top = (int)data[i + 4];
int right = (int)data[i + 5];
int bottom = (int)data[i + 6];
int classId = (int)(data[i + 1]) - 1; // Skip 0th background class id.
drawPred(classId, confidence, left, top, right, bottom, frame);
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1); // Skip 0th background class id.
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
......@@ -181,16 +189,16 @@ void postprocess(Mat& frame, const std::vector<Mat>& outs, Net& net)
int top = (int)(data[i + 4] * frame.rows);
int right = (int)(data[i + 5] * frame.cols);
int bottom = (int)(data[i + 6] * frame.rows);
int classId = (int)(data[i + 1]) - 1; // Skip 0th background class id.
drawPred(classId, confidence, left, top, right, bottom, frame);
int width = right - left + 1;
int height = bottom - top + 1;
classIds.push_back((int)(data[i + 1]) - 1); // Skip 0th background class id.
boxes.push_back(Rect(left, top, width, height));
confidences.push_back(confidence);
}
}
}
else if (outLayerType == "Region")
{
std::vector<int> classIds;
std::vector<float> confidences;
std::vector<Rect> boxes;
for (size_t i = 0; i < outs.size(); ++i)
{
// Network produces output blob with a shape NxC where N is a number of
......@@ -218,18 +226,19 @@ void postprocess(Mat& frame, const std::vector<Mat>& outs, Net& net)
}
}
}
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, 0.4f, indices);
for (size_t i = 0; i < indices.size(); ++i)
{
int idx = indices[i];
Rect box = boxes[idx];
drawPred(classIds[idx], confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
}
}
else
CV_Error(Error::StsNotImplemented, "Unknown output layer type: " + outLayerType);
std::vector<int> indices;
NMSBoxes(boxes, confidences, confThreshold, nmsThreshold, indices);
for (size_t i = 0; i < indices.size(); ++i)
{
int idx = indices[i];
Rect box = boxes[idx];
drawPred(classIds[idx], confidences[idx], box.x, box.y,
box.x + box.width, box.y + box.height, frame);
}
}
void drawPred(int classId, float conf, int left, int top, int right, int bottom, Mat& frame)
......
samples/dnn/object_detection.py
View file @ 346871e2
......@@ -31,6 +31,7 @@ parser.add_argument('--height', type=int,
parser.add_argument('--rgb', action='store_true',
help='Indicate that model works with RGB input images instead BGR ones.')
parser.add_argument('--thr', type=float, default=0.5, help='Confidence threshold')
parser.add_argument('--nms', type=float, default=0.4, help='Non-maximum suppression threshold')
parser.add_argument('--backend', choices=backends, default=cv.dnn.DNN_BACKEND_DEFAULT, type=int,
help="Choose one of computation backends: "
"%d: automatically (by default), "
......@@ -57,6 +58,7 @@ net.setPreferableBackend(args.backend)
net.setPreferableTarget(args.target)
confThreshold = args.thr
nmsThreshold = args.nms
def getOutputsNames(net):
layersNames = net.getLayerNames()
......@@ -86,36 +88,43 @@ def postprocess(frame, outs):
lastLayerId = net.getLayerId(layerNames[-1])
lastLayer = net.getLayer(lastLayerId)
classIds = []
confidences = []
boxes = []
if net.getLayer(0).outputNameToIndex('im_info') != -1: # Faster-RCNN or R-FCN
# Network produces output blob with a shape 1x1xNx7 where N is a number of
# detections and an every detection is a vector of values
# [batchId, classId, confidence, left, top, right, bottom]
assert(len(outs) == 1)
out = outs[0]
for detection in out[0, 0]:
confidence = detection[2]
if confidence > confThreshold:
left = int(detection[3])
top = int(detection[4])
right = int(detection[5])
bottom = int(detection[6])
classId = int(detection[1]) - 1 # Skip background label
drawPred(classId, confidence, left, top, right, bottom)
for out in outs:
for detection in out[0, 0]:
confidence = detection[2]
if confidence > confThreshold:
left = int(detection[3])
top = int(detection[4])
right = int(detection[5])
bottom = int(detection[6])
width = right - left + 1
height = bottom - top + 1
classIds.append(int(detection[1]) - 1) # Skip background label
confidences.append(float(confidence))
boxes.append([left, top, width, height])
elif lastLayer.type == 'DetectionOutput':
# Network produces output blob with a shape 1x1xNx7 where N is a number of
# detections and an every detection is a vector of values
# [batchId, classId, confidence, left, top, right, bottom]
assert(len(outs) == 1)
out = outs[0]
for detection in out[0, 0]:
confidence = detection[2]
if confidence > confThreshold:
left = int(detection[3] * frameWidth)
top = int(detection[4] * frameHeight)
right = int(detection[5] * frameWidth)
bottom = int(detection[6] * frameHeight)
classId = int(detection[1]) - 1 # Skip background label
drawPred(classId, confidence, left, top, right, bottom)
for out in outs:
for detection in out[0, 0]:
confidence = detection[2]
if confidence > confThreshold:
left = int(detection[3] * frameWidth)
top = int(detection[4] * frameHeight)
right = int(detection[5] * frameWidth)
bottom = int(detection[6] * frameHeight)
width = right - left + 1
height = bottom - top + 1
classIds.append(int(detection[1]) - 1) # Skip background label
confidences.append(float(confidence))
boxes.append([left, top, width, height])
elif lastLayer.type == 'Region':
# Network produces output blob with a shape NxC where N is a number of
# detected objects and C is a number of classes + 4 where the first 4
......@@ -138,15 +147,19 @@ def postprocess(frame, outs):
classIds.append(classId)
confidences.append(float(confidence))
boxes.append([left, top, width, height])
indices = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, 0.4)
for i in indices:
i = i[0]
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
drawPred(classIds[i], confidences[i], left, top, left + width, top + height)
else:
print('Unknown output layer type: ' + lastLayer.type)
exit()
indices = cv.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)
for i in indices:
i = i[0]
box = boxes[i]
left = box[0]
top = box[1]
width = box[2]
height = box[3]
drawPred(classIds[i], confidences[i], left, top, left + width, top + height)
# Process inputs
winName = 'Deep learning object detection in OpenCV'
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment