bcmi / DCI-VTON-Virtual-Try-On

[ACM Multimedia 2023] Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow.

Home Page:https://arxiv.org/abs/2308.06101

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Unable to test the warping module

RishiGitH opened this issue · comments

I am getting issue with cupy module and it's not part of the conda env yaml file

when running sh test_VITON.sh i am getting this
Screenshot 2023-10-16 at 5 28 48 PM

Also my gpu and cuda version is

Screenshot 2023-10-16 at 5 26 56 PM

Let me know how you got it working for youself . The readme seems to be missing this bit

in your case
pip install cupy-cuda12x

@dx777 getting this issue for both 12.0 and 12.1
ERROR: Could not find a version that satisfies the requirement cupy-cuda121 (from versions: none) ERROR: No matching distribution found for cupy-cuda121 ERROR: Could not find a version that satisfies the requirement cupy-cuda120 (from versions: none) ERROR: No matching distribution found for cupy-cuda120

@RishiGitH the packet is named cupy-cuda12x not cupy-cuda121
See:
https://pypi.org/project/cupy/

@dx777 Thanks got this resolved but now I am getting this issue . Is it due to image size ?

RuntimeError: Caught RuntimeError in DataLoader worker process 0. Original Traceback (most recent call last): File "/opt/conda/envs/test/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop data = fetcher.fetch(index) File "/opt/conda/envs/test/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/opt/conda/envs/test/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 51, in <listcomp> data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/ubuntu/PF-AFN/PF-AFN_test/data/cp_dataset.py", line 172, in __getitem__ parse_map = parse_map.scatter_(0, parse, 1.0) RuntimeError: Expected index [1, 576, 384] to be smaller than self [20, 512, 384] apart from dimension 0

@Limbor do you have any idea ? ^^

@RishiGitH It seems to be due to the size of the image, but I have never encountered this problem when running it on my divice. You can check whether the size of the im_parse_pil matches 512*384.

change
@cupy.util.memoize
to
@cupy.memoize
might be helpful

@RishiGitH Did you find a solution?

I am getting the same issue. What is the solution for this cupy problem?