Hi，thanks for your code.
I am having a weird problem about GPU memory.
I have four Titanx GPU, but when I use your code for training Pascal data set , even if I have reduced the batch size to 1 and use mGPUs, it still gives feed back about
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1513363039688/work/torch/lib/THC/generic/THCStorage.cu:58
Would you mind tell me why? I am not sure if that's because some part of the code has some problem>
And my cuda version is 8.0, pytorch 0.3.0,
Hi，thanks for your code. I am having a weird problem about GPU memory. I have four Titanx GPU, but when I use your code for training Pascal data set , even if I have reduced the batch size to 1 and use mGPUs, it still gives feed back about
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1513363039688/work/torch/lib/THC/generic/THCStorage.cu:58
Would you mind tell me why? I am not sure if that's because some part of the code has some problem> And my cuda version is 8.0, pytorch 0.3.0,