dylen
dylen
我使用onnx推理出来的错位了，还在debug中 
I met same problem, and I don't know how to solve. have you solved?
解决办法 net.load_state_dict(torch.load(model_path),strict=False) 加上 strict=False
AttributeError: module 'keras2onnx' has no attribute 'convert_keras'
> @lewes6369 I am using tensorrt5. > Do you manually configure the path of tensorrt (cmake ..)? Or auto. No I didn't configure the path, but it work correct
Can you release the relevant dataset files? I want to train the model on my dataset. Thanks for your great work. if you get it can you release, thank you
I have same idea you have solved?
When I excuting python main.py ,error:undefined symbol: cudnnConvolutionForward happend
> When I excuting python main.py ,error:undefined symbol: cudnnConvolutionForward happend a new error happened, ../sysdeps/x86_64/strchr.S: No such file or directory.
me too