Open ziyun126 opened 5 years ago
I'm not sure if there's a problem with the model I transformed or with the Intel sample
The Intel example was not made for tiny Yolo. You must adjust the output blob parsing...
the code has been changed now
can you help me with finding input and output node of tiny yoloV3
YOLOv3 Converted To IE IR model have three output nodes ,however YOLOv3-tiny have two output nodes, But intel OPENVINO sample "object_detection_demo_yolov3_async" if (outputInfo.size() != 3) { throw std::logic_error("This demo only accepts networks with three layers"); }