Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Where are the pose images? #14

Open
xiechun-tsukuba opened this issue Mar 25, 2024 · 2 comments
Open

Where are the pose images? #14

xiechun-tsukuba opened this issue Mar 25, 2024 · 2 comments

Comments

@xiechun-tsukuba
Copy link

xiechun-tsukuba commented Mar 25, 2024

Hi,
I can see that you need to load pose images "_pose.jpg" to train stage 2, but I can't find them in the prepared dataset you provided.

s_pose = Image.open(s_img_path.replace("/train_all_png/", "/openpose_all_img/").replace(".png", "_pose.jpg")).convert("RGB").resize(self.size, Image.BICUBIC)

Would you like to upload them to Google Drive later or do we have to generate them from the normalized_pose_txt ourselves?

Extra question: Why are we using pose "images" in stage 2 instead of coordinates as we did in stage 1? I understand that this is borrowed from ControlNet, but I would like to know the motivation behind it.

Thanks

@zhuyinna
Copy link

Hi, I can see that you need to load pose images "_pose.jpg" to train stage 2, but I can't find them in the prepared dataset you provided.

s_pose = Image.open(s_img_path.replace("/train_all_png/", "/openpose_all_img/").replace(".png", "_pose.jpg")).convert("RGB").resize(self.size, Image.BICUBIC)

Would you like to upload them to Google Drive later or do we have to generate them from the normalized_pose_txt ourselves?

Extra question: Why are we using pose "images" in stage 2 instead of coordinates as we did in stage 1? I understand that this is borrowed from ControlNet, but I would like to know the motivation behind it.

Thanks

Hi,have you solve this problem? I have same question too.

@xiechun-tsukuba
Copy link
Author

Hi, I can see that you need to load pose images "_pose.jpg" to train stage 2, but I can't find them in the prepared dataset you provided.

s_pose = Image.open(s_img_path.replace("/train_all_png/", "/openpose_all_img/").replace(".png", "_pose.jpg")).convert("RGB").resize(self.size, Image.BICUBIC)

Would you like to upload them to Google Drive later or do we have to generate them from the normalized_pose_txt ourselves?
Extra question: Why are we using pose "images" in stage 2 instead of coordinates as we did in stage 1? I understand that this is borrowed from ControlNet, but I would like to know the motivation behind it.
Thanks

Hi,have you solve this problem? I have same question too.

Unfortunately, I have never got any reply from them.
I guess nobody is maintaining this repo anymore.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants