yikang-li / FactorizableNet

Factorizable Net (Multi-GPU version): An Efficient Subgraph-based Framework for Scene Graph Generation
216 stars 38 forks source link

cuda out of memory while testing #22

Closed Freya-Cui closed 5 years ago

Freya-Cui commented 5 years ago

Hello, I'm trying to test using the pretrained model, but the error appeared after testing 1000 images, and my GPU has 10986MiB memory: RuntimeError: CUDA out of memory. Tried to allocate 957.12 MiB (GPU 0; 10.73 GiB total capacity; 8.16 GiB already allocated; 801.19 MiB free; 865.05 MiB cached) How could I solve this problem? How much memory needed for testing?

digbose92 commented 4 years ago

@Freya-Cui were you able to solve the cuda out of memory issue ?

muraliadithya commented 4 years ago

@Freya-Cui Where did you add the 'with torch.no_grad()' ? Could you tell me the file name and the line number?