Failed to convert torch model to onnx format model

[XueweiHan21]

The pth model is trained on the gpu and converted to onnx on the cpu. The current compiled code reports an error:

root@9b04f5972f0e:/mnt/test_model/resnet50/resnet50_pytorch# bash run_compile.sh
2021-11-23 08:43:00.368629: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library libcudart.so.11.0
Source type: TorchModelFile.
Target type: ONNXModel.
Compile path: TorchModelFile -> OnnxModel -> ONNXModel.
Compiling to OnnxModel...
/usr/local/lib/python3.6/dist-packages/torch/cuda/init.py:52: UserWarning: CUDA initialization: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx (Triggered internally at /pytorch/c10/cuda/CUDAFunctions.cpp:100.)
return torch._C._cuda_getDeviceCount() > 0
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/model_compiler/init.py", line 13, in compile_model
'path': compiler.compile_from_json(config)
File "/usr/local/lib/python3.6/dist-packages/model_compiler/compiler.py", line 50, in compile_from_json
target_model = compiler(source=source_type.from_json(value), config=compiler_config_type.from_json(value))
File "/usr/local/lib/python3.6/dist-packages/model_compiler/compilers/repository.py", line 118, in _compiler
result = edge.compiler(result, inner_config)
File "/usr/local/lib/python3.6/dist-packages/model_compiler/compilers/torch_model_file_to_onnx_model.py", line 85, in compile_source
model.load_state_dict(torch.load(source.model_path))
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 594, in load
return _load(opened_zipfile, map_location, pickle_module, **pickle_load_args)
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 853, in _load
result = unpickler.load()
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 845, in persistent_load
load_tensor(data_type, size, key, _maybe_decode_ascii(location))
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 834, in load_tensor
loaded_storages[key] = restore_location(storage, location)
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 175, in default_restore_location
result = fn(storage, location)
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 151, in _cuda_deserialize
device = validate_cuda_device(location)
File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 135, in validate_cuda_device
raise RuntimeError('Attempting to deserialize object on a CUDA '
RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device('cpu') to map your storages to the CP
`