Closed zulihit closed 2 years ago
Hi, yes, this is caused by the mismatched environment setting. So It should be best to use the same environment. You could create the environment with conda/venv.
Thank you for your response, I have now created the same environment. I also want to ask if I want to run on Windows 10, do I need to run main.py? How can I get the results, thank you again.
Sure, you need to run the script no matter which OS you are using. Just follow the instruction to put in your custom data and run the script.
Hello I get the same error:
RuntimeError: softmax() Expected a value of type 'Optional[Tensor]' for argument 'ptr' but instead found type 'int'.
Position: 2
Value: 48
Declaration: softmax(Tensor src, Tensor? index=None, Tensor? ptr=None, int? num_nodes=None, int dim=0) -> (Tensor)
Cast error details: Unable to cast Python instance to C++ type (compile in debug mode for details)
Why the code cannot work with my environment ? It is the first time I ever encounter that type of error... I have CUDA 11.3 and PyTorch 1.10.2.
Thanks for your help !
Hello, thank you for your creative paper, which is very helpful to me. I had some problems running your codes,may I ask for some advice?