acheng

Error 'RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) ' in line 147 of train_retrieval.py

1

Thank you for your work. May I ask how I can make the necessary changes if you encounter the above issue? Do you have any suggestions you can give me?

Inference time is longer than training time

1

My training time is much shorter than my reasoning time. Would you like to inquire if this situation is normal? Or what advice can you give me. Training Code： loss...

About the weight file of prior

2

Hello, thank you very much for your work! I would like to use the pre trained prior model for my own research and would like to ask which link is...

Thank you for your work! I didn't find the inference.py file.

训练时，遇到错误' RuntimeError(f"Input {texts[i]} is too long for context length {context_length}")'

8

感谢你的工作，在我训练flickr30k时，总是在中间中断，并报上述错误，想请问您是否有什么需要修改的或者一些别的建议能给到我。多有打扰，感谢！