muelea / shapy

CVPR 2022 - Official code repository for the paper: Accurate 3D Body Shape Regression using Metric and Semantic Attributes.
https://shapy.is.tue.mpg.de/
305 stars 44 forks source link

HOTO? #44

Open Rut-B opened 6 months ago

Rut-B commented 6 months ago

I'm trying to figure out how to run the shapy model on my own RGB images, without needing any additional files like keypoints or vertices.

I would greatly appreciate it if you could provide me an explanation of how to run the code with my RGB images only - to get the measurements of the body

Rut-B commented 6 months ago

@vchoutas @vchoutas @pixelite1201

Rut-B commented 6 months ago

I succeeded to run this cmd on the collab notebook

%%shell cd /content/shapy/regressor python demo.py --save-vis true --save-params true --save-mesh true --split test --datasets openpose --output-folder samples/shapy_fit_ruti/ --exp-cfg configs/b2a_expose_hrnet_demo.yaml --exp-opts output_folder=../data/trained_models/shapy/SHAPY_A part_key=pose datasets.pose.openpose.data_folder=../samples datasets.pose.openpose.img_folder=image datasets.pose.openpose.keyp_folder=openpose datasets.batch_size=1 datasets.pose_shape_ratio=1.0

muelea commented 6 months ago

You need to adapt the data processing script to do that. We use the keypoint file to crop the person on the picture. If you have a picture that is already cropped you can skip this step in the data loader.

Rut-B commented 6 months ago

@muelea thanks of your response!! if just have RGB image that not was copped. should I prepare anything? what is the cmd running in order to use the Shapy to get the measurements body from RGB wild image?

python demo.py --save-vis true --save-params true --save-mesh true --split test --datasets openpose --output-folder ../samples/shapy_fit/ --exp-cfg configs/b2a_expose_hrnet_demo.yaml --exp-opts output_folder=../data/trained_models/shapy/SHAPY_A part_key=pose datasets.pose.openpose.data_folder=../samples datasets.pose.openpose.img_folder=images
datasets.pose.openpose.keyp_folder=openpose datasets.batch_size=1 datasets.pose_shape_ratio=1.0

what are this parameters? datasets.pose.openpose.data_folder=../samples datasets.pose.openpose.img_folder=images
datasets.pose.openpose.keyp_folder=openpose

is it should be specific for the images?

Rut-B commented 6 months ago

@muelea I would greatly appreciate it if you could provide me an explanation