Open xiechun-tsukuba opened 7 months ago
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.
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.
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. https://github.com/tencent-ailab/PCDMs/blob/8f6fc8195a75717fc9302f5aefee5d278a162dff/src/dataset/stage2_dataset.py#L99
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.
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. https://github.com/tencent-ailab/PCDMs/blob/8f6fc8195a75717fc9302f5aefee5d278a162dff/src/dataset/stage2_dataset.py#L99
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