search

YoungXIAO13 / FewShotDetection

(ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild"
http://imagine.enpc.fr/~xiaoy/FSDetView/
MIT License
212 stars 33 forks source link

bash run/train_voc_first.sh #38

Open chh6936 opened 3 years ago

chh6936 commented 3 years ago

2021-04-22 15-21-27屏幕截图 When I run this step bash run/train_voc_first.sh, it appears as shown in the figure. It has been in this state for a day. I don't know how to solve it. Can you help me？Thank you.

YoungXIAO13 commented 3 years ago

It appears not very clear to me where could come from the error, maybe you can do a monitoring of the GPU running state with nvidia-smi to check if the training has already started? If not, maybe it's better to go step by step to spot the issue

chh6936 commented 3 years ago

It appears not very clear to me where could come from the error, maybe you can do a monitoring of the GPU running state with nvidia-smi to check if the training has already started? If not, maybe it's better to go step by step to spot the issue

I use nvidia-smi to check the running status of GPU. I find that the GPU is not working, but the terminal always displays the status of the above picture, and it does not report any errors. Where should I check for errors? Thank you.

YoungXIAO13 commented 3 years ago

Maybe the first thing to check is wether the code has gone from line-321 to the training loops in line-399.

For a step-by-step debugging, you could use the ipdb libraries. Hope that will help you.

WqxLoveCoding commented 2 years ago

hello, have you fixed it yet? I met the same problem with you, but my nvidia-smi shows that it's working

WqxLoveCoding commented 2 years ago

it remains like this 屏幕截图 2022-04-11 093343

WqxLoveCoding commented 2 years ago

@YoungXIAO13 @chh6936