Error CUDA out of memory

RuntimeError: CUDA out of memory. Tried to allocate 2.00 MiB (GPU 0; 15.90 GiB total capacity; 15.05 GiB already allocated; 3.81 MiB free; 154.34 MiB cached)

Someone can explain to me how to free the CUDA memory in PyTorch?

I am also getting the same error, I am using 2080Ti for my training, I think It’s Because of Data size i.e., Image size., in my case I am using 2448*1564 image and coco type Annotation with unet_learner having BS=1 … Data size is my wild guess… Is there any mapping function available for Bbox coordinates in fastai?? If there Plase guide me.

try assert = False in a cell . This should work