out of memory when extracting patches from Oxford dataset

[SikaStar]

Hi,
I have used your code from examples/hesaffnet/WBS demo.ipynb'to extract patches and descriptors from the Oxford dataset, however when I set USE_CUDA = True, num_features=3000, the error follows:

Traceback (most recent call last):
  File "/home/dyx/workspace/affnet/examples/hesaffnet/123.py", line 103, in <module>
    detector_time, descriptors_time = get_geometry_and_descriptors(img, detector, descriptor)
  File "/home/dyx/workspace/affnet/examples/hesaffnet/123.py", line 69, in get_geometry_and_descriptors
    patches = detector.extract_patches_from_pyr(LAFs, PS = 32)
  File "/home/dyx/workspace/affnet/examples/hesaffnet/SparseImgRepresenter.py", line 178, in extract_patches_from_pyr
    PS = PS)
  File "/home/dyx/workspace/affnet/examples/hesaffnet/LAF.py", line 218, in extract_patches_from_pyramid_with_inv_index
    patches[cur_lvl_idxs,:,:,:] = extract_patches(scale_pyramid[i][j], LAFs[cur_lvl_idxs, :,:], PS )
  File "/home/dyx/workspace/affnet/examples/hesaffnet/LAF.py", line 200, in extract_patches
    return torch.nn.functional.grid_sample(img.expand(grid.size(0), ch, h, w),  grid)  
  File "/home/dyx/anaconda2/lib/python2.7/site-packages/torch/nn/functional.py", line 995, in grid_sample
    return GridSampler.apply(input, grid)
  File "/home/dyx/anaconda2/lib/python2.7/site-packages/torch/nn/_functions/vision.py", line 27, in forward
    input = input.contiguous()
RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1503966894950/work/torch/lib/THC/generic/THCStorage.cu:66

Process finished with exit code 1

and when I set num_features=1000 it will be OK, could you tell me how to solve it?
Thanks a lot!

[ducha-aiki]

That seems that you don`t have enough GPU memory. The only solution is to set USE_CUDA to False.

I have an implementation, which do things is batches, but it works only with latest github PyTorch, not pip one. So if I apply changes, it would break compatibility, which I don`t want
But you can try to replace all grid_apply functions with this one:

https://gist.github.com/ducha-aiki/9f457f80298c52aa65819fe235f9cec1

[SikaStar]

@ducha-aiki
That's great! Thank you very much!

[gsygsy96]

Can't reach your address ---- 'https://gist.github.com/ducha-aiki/9f457f80298c52aa65819fe235f9cec1'
Could u give me the updated address? @SikaStar @ducha-aiki

[ducha-aiki]

@shanYanGuan address you have works