I have a PyTorch model and I want to refit some layers at runtime. I have set layer names when exporting the PyTorch model to ONNX format. However, I failed to refit layers. It seems that the layer names are never set when ONNXParser parse the ONNX file.
Is there any option to force ONNXParser set layer names according to ONNX names? I know I can set all layer names manually after ONNXParser.parse called.