Closed yspisgod closed 2 years ago
when i run python3 /opt/intel/openvino_2021.3.394/deployment_tools/model_optimizer/mo.py --input_model yolov5s.onnx --input_shape [1,3,640,640] --output_dir ./openvino --data_type FP32 --output Conv_253,Conv_302,Conv_351
it seems that "-output" is unnecessary
Output node names are different in different environment, and yolov5 version. Check the output node name in Netron.
We remove the yolov5 head layers through model conversion, so '--output' is mandatory.
when i run python3 /opt/intel/openvino_2021.3.394/deployment_tools/model_optimizer/mo.py --input_model yolov5s.onnx --input_shape [1,3,640,640] --output_dir ./openvino --data_type FP32 --output Conv_253,Conv_302,Conv_351
it seems that "-output" is unnecessary