python /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py --input_model "model.onnx" --output_dir "cur_folder/"
[ ERROR ] The ExpandDims node Unsqueeze_583 has more than 1 input
[ ERROR ] Cannot infer shapes or values for node "Slice_4".
[ ERROR ] Output shape: [0 3 0 0] of node "Slice_4" contains non-positive values
[ ERROR ] It can happen due to bug in custom shape infer function .
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
Há três nós de saída no YOLOv5 e todos eles precisam ser especificados no comando:
Comando Model Optimizer: python mo.py -input_model model.onnx --nós de saída --input_shape [1,3.512.512]
Use a Netron para visualizar o peso YOLOv5 ONNX.