RuntimeError: cuda runtime error : out of memory

1

I even tried with batch_size = 1 still I get this error

RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1512378360668/work/torch/lib/THC/generic/THCStorage.cu:58

What are the possible reasons for this error than GPU running out of memory?

GPU used: GTX 1080Ti

2

GPU was really running out of memory. I reduced the number of residual blocks and it worked.