minar09 / cp-vton-plus

Official implementation for "CP-VTON+: Clothing Shape and Texture Preserving Image-Based Virtual Try-On", CVPRW 2020
https://minar09.github.io/cpvtonplus/
MIT License
352 stars 121 forks source link

generate pose #38

Closed dnalexen closed 2 years ago

dnalexen commented 3 years ago

Hello, is it possible to have the code that you used to generate the pose keypoints? I try to generate the keypoints of some image of the cp-vton+ with the code on this github repository: https://github.com/minar09/openpose-pytorch. However, I do not find the same points as the ones in the cp-viton+ dataset.

minar09 commented 3 years ago

https://github.com/minar09/cp-vton-plus/blob/master/README.md#testing-with-custom-images

JahangirButt-BU commented 3 years ago

@minar09 which version of openpose should i use to genenrate the keypoints?

minar09 commented 3 years ago

@JahangirButt-BU , you can use any version from the official openpose, just be sure to generate with COCO-18 model.

JahangirButt-BU commented 3 years ago

@minar09 yes i did generte json file using coco-18 model but in the latest version they change the output json file format

json file using openpose 1.7.0: https://pastebin.com/jrLBEVG9 used: https://github.com/CMU-Perceptual-Computing-Lab/openpose

minar09 commented 3 years ago

I think it will be okay if you just change "pose_keypoints" in the cp_dataset.py into "pose_keypoints_2d".

JahangirButt-BU commented 3 years ago

@minar09 Thankyou very much its works..

echoi3 commented 3 years ago

Could you let me know what command(s) did you use to generate 18 key points from coco-18 model? I keep getting 25 key points, which seems to be set as a default, and can't change the command to generate 18 points.

JahangirButt-BU commented 3 years ago

Could you let me know what command(s) did you use to generate 18 key points from coco-18 model? I keep getting 25 key points, which seems to be set as a default, and can't change the command to generate 18 points.

"#./build/examples/openpose/openpose.bin --image_dir /home/fyp/Desktop/Try_On#4/data/test/image --model_pose COCO --write_json /home/fyp/Desktop/Try_On#4/data/test/pose" i used this command to generate the required points