Gyojung Gu

@sankalp2K We use "densepose_rcnn_R_50_FPN_s1x" model in the [detectron2](https://github.com/facebookresearch/detectron2) repository :)

I think I can't confirm the performance because I haven't trained it with a dataset including the full body. The recently released DressCode dataset contains the full body, so I...

@kelisiya I just committed the code for a parse agnostic image. Please check the code :) And our dataset code contains the process for a clothing-agnostic human image.

@kinivi Hello, I use the model on "https://github.com/OPHoperHPO/image-background-remove-tool". For the detail, please check the Preprocess.md :)

Unfortunately, even I have difficulty reproducing densepose images exactly on the dataset. I am currently working on a new dataset using the densepose image obtained by DumpAction in 'apply_net.py'. It...

Hello @hyyuan123. You can check 'Preprocess.md' for the detailed preprocess :)

@srckid I have no idea because I didn't have the problem you reported while training. If you changed the code or dataset, I will think about the reasons if you...

Hello guys. I just created 'Preprocess.md', the description for our preprocess including human parsing. Please check it :)

Hello guys. You can check the detailed command line operation I used for the openpose. Please check it :)

Hello guys. I just created 'Preprocess.md', the description for our preprocess including human parsing. Please check it :)