Where are the pose images?

[xiechun-tsukuba]

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.

PCDMs/src/dataset/stage2_dataset.py

Line 99 in 8f6fc81

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]

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.

PCDMs/src/dataset/stage2_dataset.py

Line 99 in 8f6fc81

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]

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.

PCDMs/src/dataset/stage2_dataset.py

Line 99 in 8f6fc81

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.

[Uaena-cf]

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.您好，我可以看到您需要加载姿势图像“_pose.jpg”来训练第 2 阶段，但我在您提供的准备好的数据集中找不到它们。

PCDMs/src/dataset/stage2_dataset.py

Line 99 in 8f6fc81

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?您想稍后将它们上传到 Google 云端硬盘还是我们必须自己从 normalized_pose_txt 生成它们？
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.额外问题：为什么我们在阶段 2 中使用姿势“图像”而不是像阶段 1 中那样使用坐标？我知道这是从 ControlNet 借用的，但我想知道其背后的动机。
Thanks 谢谢

Hi，have you solve this problem? I have same question too.你好，这个问题你解决了吗？我也有同样的问题。

Unfortunately, I have never got any reply from them.不幸的是，我从未收到他们的任何回复。 I guess nobody is maintaining this repo anymore.我想没有人再维护这个仓库了。

Hello, I encountered the same issue. How did you finally resolve this problem?

[muzishen]

Sorry for the late reply! You can directly use the OpenPose implementation from the repository https://github.com/huggingface/controlnet_aux to generate poses. I will also upload a set of pre-generated pose images in the near future.