Context-Transformer
Context-Transformer copied to clipboard
Pretraining RFBNet on source domain dataset COCO60, it shows loss nan
Hello, I really appreciate your work! When I pretrain RFBNet on source domain dataset COCO60, it shows loss nan. Is it correct and why?
I have the same problem from iter2940...Is there anybody know why?
Hello ,I've asked my classmate, they told me the exploding gradient may cause this problem.
Hi, do you make any modifications to the code? If so, please first try with the original code.
Hi, do you make any modifications to the code? If so, please first try with the original code.
Thanks a lot for your reply~!!! Due to my computer's GPU memory is small , I've got 'CUDA out of memory ' error when running the original code,so I changed the batch size to 32, then pretrain RFBNet on source domain dataset COCO60, and met the same problem of LexieYang's.
I will verify it and get back to you soon.
I will verify it and get back to you soon.
Thank you!!!!:blush:
Hello! I am encountering the same problem, have there been any updates regarding this?