Should create a pull request?

[AdarshMJ]

Hi Nick!

When you try to run the code on a non-cuda device like for example - MacBook Pro, I keep getting this error

File "/Users/adarsh/anaconda/envs/py36/lib/python3.6/site-packages/torch/cuda/init.py", line 75, in _check_driver raise AssertionError("Torch not compiled with CUDA enabled") AssertionError: Torch not compiled with CUDA enabled

To fix this you can edit line 88 in STROTSS/utils.py from return tensor.cuda() to return tensor And also change stylize_objectives.py line 15 from self.z_dist = torch.zeros(1).cuda() to self.z_dist = torch.zeros(1)

And starts working fine again. However GPU can definitely speed up the process. Thought should include this for anyone who might be facing this problem. Thanks in advance!

[nkolkin13]

Hi Adarsh, I wrote the code assuming it would only be run on computers with a GPU, otherwise it would be extremely slow. But it's easy enough for me to add a flag for a cpu only version, so I'll push an update in the next few days. I'll leave this issue open and reply to it once I've added the flag. Best, Nick