RuntimeError: cuda runtime error (2) : out of memory

[Nandan91]

While testing the RGBDiff model using the command
python test_models.py ucf101 RGBDiff /media/sda/nandan/data/ucf101_rgb_val_split_1.txt ucf101_bninception__rgbdiff_checkpoint.pth.tar --arch BNInception --save_scores SCORE_UCF101_1_RGBDIFF --workers=2
I'm getting this error
Traceback (most recent call last):
File "test_models.py", line 130, in
rst = eval_video((i, data, label))
File "test_models.py", line 117, in eval_video
rst = net(input_var).data.cpu().numpy().copy()
File "/home/nandan/anaconda2/lib/python2.7/site-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "/home/nandan/anaconda2/lib/python2.7/site-packages/torch/nn/parallel/data_parallel.py", line 73, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/nandan/anaconda2/lib/python2.7/site-packages/torch/nn/parallel/data_parallel.py", line 83, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/nandan/anaconda2/lib/python2.7/site-packages/torch/nn/parallel/parallel_apply.py", line 67, in parallel_apply
raise output
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1518238409320/work/torch/lib/THC/generic/THCStorage.cu:58

I'm using two K40 GPU with each global memory capacity 4742MiB.

[Nandan91]

@yjxiong : I found that runtime memory problem can be solved either by reducing --test_crops size or by reducing --test_segments size . My question is which one to prefer ? I mean which one won't affect test accuracy ?

[wj320]

I have met the same problem. How did you solve it? @Nandan532189

[yjxiong]

The test_crops is the preferred one. It does not lead to a drastic decrease in accuracy.