search

tomassosorio / OCR_tablenet

TableNet Implementation on Pytorch
144 stars 45 forks source link

RuntimeError: CUDA out of memory. #3

Closed dajor closed 3 years ago

dajor commented 3 years ago

Tried to allocate 1.91 GiB (GPU 0; 7.93 GiB total capacity; 5.33 GiB already allocated; 1.91 GiB free; 5.36 GiB reserved in total by PyTorch)

When i try to run python train.py

tomassosorio commented 3 years ago

Reduce de batch size or the image resolution during inference.

The Vram of your GPU is not enough for what you pretend to do.