I am testing an onnx model exported from the PyTorch.
The export is successed
torch.onnx.export(net, args=input_tensor, f=onnx_file_name, input_names=["input_0"], output_names=["output_0"], operator_export_type=OperatorExportTypes.ONNX_ATEN_FALLBACK, opset_version=11)
but with some warning:
C:\Users\bigtree\.conda\envs\segmentaionv01\lib\site-packages\torch\onnx\utils.py:243: UserWarning: `add_node_names' can be set to True only when 'operator_export_type' is `ONNX`. Since 'operator_export_type' is not set to 'ONNX', `add_node_names` argument will be ignored.
"`{}` argument will be ignored.".format(arg_name, arg_name))
C:\Users\bigtree\.conda\envs\segmentaionv01\lib\site-packages\torch\onnx\utils.py:243: UserWarning: `do_constant_folding' can be set to True only when 'operator_export_type' is `ONNX`. Since 'operator_export_type' is not set to 'ONNX', `do_constant_folding` argument will be ignored.
"`{}` argument will be ignored.".format(arg_name, arg_name))
C:\Users\bigtree\Documents\prototype\segmentation\segmentaion_simple_make_onnx_eval\yolact.py:273: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
for j, i in product(range(conv_h), range(conv_w)):
C:\Users\bigtree\Documents\prototype\segmentation\segmentaion_simple_make_onnx_eval\yolact.py:301: TracerWarning: torch.Tensor results are registered as constants in the trace. You can safely ignore this warning if you use this function to create tensors out of constant variables that would be the same every time you call this function. In any other case, this might cause the trace to be incorrect.
self.priors = torch.Tensor(prior_data).view(-1, 4)
C:\Users\bigtree\Documents\prototype\segmentation\segmentaion_simple_make_onnx_eval\yolact.py:301: TracerWarning: Converting a tensor to a Python float might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
self.priors = torch.Tensor(prior_data).view(-1, 4)
C:\Users\bigtree\Documents\prototype\segmentation\segmentaion_simple_make_onnx_eval\layers\functions\detection.py:73: TracerWarning: Converting a tensor to a Python index might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
for batch_idx in range(batch_size):
C:\Users\bigtree\Documents\prototype\segmentation\segmentaion_simple_make_onnx_eval\layers\functions\detection.py:98: TracerWarning: Converting a tensor to a Python boolean might cause the trace to be incorrect. We can't record the data flow of Python values, so this value will be treated as a constant in the future. This means that the trace might not generalize to other inputs!
if scores.size(1) == 0:
Succesfully created FBB_float32_code11.onnx
When I run the onnx model in onnxrumtime
sess = rt.InferenceSession(model_path)
I got:
File "make_onnx.py", line 1268, in evalvideo_onnx
sess = rt.InferenceSession(model_path)
File "C:\Users\bigtree\.conda\envs\segmentation01\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 280, in __init__
self._create_inference_session(providers, provider_options)
File "C:\Users\bigtree\.conda\envs\segmentation01\lib\site-packages\onnxruntime\capi\onnxruntime_inference_collection.py", line 307, in _create_inference_session
sess = C.InferenceSession(session_options, self._model_path, True, self._read_config_from_model)
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from yolact_FBB_float32_code11_RI.onnx failed:Node () Op (SequenceConstruct) [TypeInferenceError] Input type for input at index 0 is null. Type info is expected.
I am not very familiar with the underneath logic of the pytorch->onnx conversion. I wonder is this error relates to the previous warnings?
I suspect it may related to the first warning but not sure.
Anyone could give suggestion about the warnings/error and how to remove them will be appreciated.