tianchi_lvcai
tianchi_lvcai copied to clipboard
Cuda out of memory even batch size is reduced to 2
I still have the cuda out of memory issue after I reduce the batch size:
RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0; 2.00 GiB total capacity; 1.25 GiB already allocated; 3.55 MiB free; 1.27 GiB reserved in total by PyTorch)
Any suggestions?