chengven027
chengven027
Why do I feel like it is right? from the file: https://github.com/onnx/onnx/blob/main/docs/Operators.md#ConvTranspose ``` `pads` format should be as follow [x1_begin, x2_begin...x1_end, x2_end,...] ``` convtranspose_pads: ` x (1,1,3,3,) w(1,2,3,3) , strides(3,2),...
@kparzysz-quic Looks like CI has a error. Can you help check it ? thanks.
@masahi Could you review the fix again? thanks.
Dose this PR need to be reviewed again? @AndrewZhaoLuo @leandron
I am sorry, I really can't create an unit test with empty string of `constant_value`. @leandron @AndrewZhaoLuo
@AndrewZhaoLuo Yes, I tried many times but I got the same error as yours. `onnxruntime.capi.onnxruntime_pybind11_state.InvalidGraph: [ONNXRuntimeError] : 10 : INVALID_GRAPH : This is an invalid model. Type Error: Type 'tensor(string)'...
> Can you share your model by any chance? Can you also run your model via ONNX-RT? [coat_model.zip](https://github.com/apache/tvm/files/9474424/coat_model.zip) 1. model have been uploaded. 2. The model can pass by ONNX-RT....
Hey, @AndrewZhaoLuo Have you seen this PR, and any update with me? thanks.
Actually I ran into this problem while inferring an already existing onnx model. The model is `GLADNet`. And I import it in TVM. Then I got two result, one is...
op input: [array([[[0.7809397 , 0.91295964, 0.510135 , 0.7067488 , 0.45204508, 0.74113446, 0.57529855, 0.17431349, 0.59966135, 0.18572877, 0.2826753 , 0.34644118, 0.8569564 , 0.5671829 , 0.5620156 , 0.07336127, 0.83321315, 0.0343755 , 0.86830616, 0.3005494...