MosbehBarhoumiRAI

Could someone who has attempted the method proposed by @maguro27 please verify if the shape of data[0]["pred_densepose"][0].labels is indeed torch.Size([244, 82])? Alternatively, please let me know if I have overlooked...

Hello @Malthehave and @trthminh , I wanted to share two resources with you that I found on Github. The first one is an openpose.ipynb file that you can find at...

@ljcljc I believe it's not possible to run OpenPose on Google Colab, despite trying various methods. However, I switched to the [PyTorch version](https://github.com/beingjoey/pytorch_openpose_body_25) of OpenPose, which has limited keypoints for...

Hello @lujiazho , I appreciate the effort you've put in. I would like to inquire about 'image-parse-agnostic-v3.2', Have you attempted to train the HR-VITON model using this approach? Specifically, I...

Just trying to help you @Mingy123 , I thnik it will be simpler to use this cleaned code for [CIHP_PGN](https://drive.google.com/drive/folders/1XVDSnH-iihMkstaSMK3GNxqLEwwMdRnR), aslo I would like to mention that the output will...

@OliverVarnce @lujiazho Is there a way to run CIHP_PGN on Google Colab, considering that the original code is written in TensorFlow 1.x and I am encountering difficulties while trying to...

@zxjzzz The input directory of Kaggle is in read-only mode. I suggest that the error might be due to YOLO attempting to create something in that folder (maybe the 'train'...

@glenn-jocher Thanks for your detailed answer. I'm currently doing exactly that, though I thought there might be a more efficient way to save even more time.

Hello @hyyuan123 I am planning to train the same model using a larger dataset. I am wondering if the problem with training still exists. If not, how did you resolve...

Hello @ajmairkashif I have recently utilized this repository: https://github.com/Hzzone/pytorch-openpose. I found that by commenting out the line 'canvas = util.draw_handpose(canvas, all_hand_peaks)' in the demo.py file, the resulting skeleton output remains...