search

yijingru / ASSD-Pytorch

[CVIU 2019] ASSD learns to highlight useful regions on the feature maps while suppressing the irrelevant information, thereby providing reliable guidance for object detection.
39 stars 20 forks source link

RuntimeError #24

Open myfamily111 opened 1 year ago

myfamily111 commented 1 year ago

RuntimeError: CUDA out of memory. Tried to allocate 52.00 MiB (GPU 0; 11.77 GiB total capacity; 7.07 GiB already allocated; 44.06 MiB free; 7.21 GiB reserved in total by PyTorch)

yijingru commented 1 year ago

You may want to adjust batch size to fit GPU memory

myfamily111 commented 1 year ago

I adjusted batch size but the error still exists.

---Original--- From: @.> Date: Wed, Mar 22, 2023 14:37 PM To: @.>; Cc: @.**@.>; Subject: Re: [yijingru/ASSD-Pytorch] RuntimeError (Issue #24)

You may want to adjust batch size to fit GPU memory

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

yijingru commented 1 year ago

It looks like 7G out of 11.77 G are occupied in your case. It may be too small for this task.

myfamily111 commented 1 year ago

OK!Thank you!

---Original--- From: @.> Date: Wed, Mar 22, 2023 14:48 PM To: @.>; Cc: @.**@.>; Subject: Re: [yijingru/ASSD-Pytorch] RuntimeError (Issue #24)

It looks like 7G out of 11.77 G are occupied in your case. It may be too small for this task.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>