将pytorch模型.pth导出为onnx格式时报错，源代码如下：
错误信息如下
Traceback (most recent call last):
File "111.py", line 17, in <module>
torch.onnx.export(model,dummy_input,"yolov3.onnx",input_names=['images'],output_names=['outTensors'],export_params=True,training=False)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/__init__.py", line 25, in export
return utils.export(*args, **kwargs)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 131, in export
strip_doc_string=strip_doc_string)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 363, in _export
_retain_param_name, do_constant_folding)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 278, in _model_to_graph
_disable_torch_constant_prop=_disable_torch_constant_prop)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 188, in _optimize_graph
graph = torch._C._jit_pass_onnx(graph, operator_export_type)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/__init__.py", line 50, in _run_symbolic_function
return utils._run_symbolic_function(*args, **kwargs)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/utils.py", line 589, in _run_symbolic_function
return fn(g, *inputs, **attrs)
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/symbolic.py", line 130, in wrapper
args = [_parse_arg(arg, arg_desc) for arg, arg_desc in zip(args, arg_descriptors)]
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/symbolic.py", line 130, in <listcomp>
args = [_parse_arg(arg, arg_desc) for arg, arg_desc in zip(args, arg_descriptors)]
File "/home/xyj/.local/lib/python3.6/site-packages/torch/onnx/symbolic.py", line 90, in _parse_arg
raise RuntimeError("Failed to export an ONNX attribute, "
RuntimeError: Failed to export an ONNX attribute, since it's not constant, please try to make things (e.g., kernel size) static if possible
解决方案：将pytorch版本从1.1.0降为1.0.1
先查看此时的pytorch版本
然后安装1.0.1版本
sudo pip3 install torch==1.0.1-fhttps://download.pytorch.org/whl/cu90/stable
并查看版本信息
然后再次运行就不会出现上述错误
网友评论