Received Node-Related Errors When Converting YOLOv5 ONNX Model into Intermediate Representation (IR) Format

• Converted YOLOv5 ONNX model into IR format:

  python /opt/intel/openvino_2021/deployment_tools/model_optimizer/mo.py --input_model "model.onnx" --output_dir  "cur_folder/"

• Received error:

  [ 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 <function Slice.infer at 0x7fda43996f70>.
  [ 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).

There are three output nodes in YOLOv5 and all of them need to be specified in the command:

Model Optimizer command: python mo.py --input_model model.onnx --output <output nodes> --input_shape [1,3,512,512]

Use Netron to visualize the YOLOv5 ONNX weight.