search

ubc-vision / COTR

Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)
Apache License 2.0
464 stars 58 forks source link

Question #14

Closed Lucifer1002 closed 3 years ago

Lucifer1002 commented 3 years ago

Hello, when running through the code with the pre-trained model, it appears that RuntimeError: CUDA out of memory. Tried to allocate 2.00 GiB (GPU 0; 7.79 GiB total capacity; 2.90 GiB already allocated; 1.83 GiB free; 4.80 GiB reserved in total by PyTorch).Is there any solution？For example, which parameters to adjust？

jiangwei221 commented 3 years ago

Have you tried to set the parameter to False? https://github.com/ubc-vision/COTR/blob/682db5a4303a1ecfd5a201709671b593ae0071b0/COTR/inference/inference_helper.py#L19

Lucifer1002 commented 3 years ago

Thank you very much, your method is effective！