Closed s-s-wang closed 3 years ago
did you solve that? if yes, could you please tell me how you solved it? (reduce the batch size?)
you should either reduce your batch_size or reduce the input_h and input_w in the train.py where the dataset is loaded
After executive the train command, it report error "RuntimeError: CUDA out of memory. Tried to allocate 182.00 MiB (GPU 0; 7.79 GiB total capacity; 6.52 GiB already allocated; 127.31 MiB free; 69.56 MiB cached)".