everybody_dance_now_pytorch
everybody_dance_now_pytorch copied to clipboard
Lotayou
A PyTorch Implementation of "Everybody Dance Now" from Berkeley AI lab.
Hello, I seem to have found a problem when trying to train hign-resolution video. After I resized the normal video at 512*512 resolution to 1024*1024, I found that some rectangular...
Thank you for your work! I have downloaded a Bruno Mars video and resize it to 288*512, but I can't correctly get the coordinates with ./pose_estimator and I found there...
There is a typo in compute_coordinates_for_video line 249. It should read: if not os.path.isdir(pose_dir):
I am running into this syntax error when running the compute_coordinates_for_video.py  My datasets/train_B just contains a bunch of images extracted from video  Please kindly let me know why...
```torch.utils.serialization.load_lua``` no longer supported so I have fixed it by including https://github.com/bshillingford/python-torchfile Now its working fine with latest Pytorch versions
I got the error when runing `python ./pose_estimator/compute_coordinates_for_video.py`: `2020-09-02 08:55:35.129558: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory...
I execute the script sh ./scripts/test_full_512.sh Then appear the error as follows: /media/ouc/4T_B/gc/everybody_dance_now_pytorch/models/pose2vidHD_model.py:146: UserWarning: volatile was removed and now has no effect. Use `with torch.no_grad():` instead. input_label = Variable(input_label, volatile=infer)...
thank you for the work,can you give your result video demo,I want to compared it to vid2vid,because I use vid2vid to pose transefer.
