/WiLoR-mini

WiLoR hand 3d pose estimation! Simplifying WiLoR into a python package！

Primary LanguagePython

WiLoR-mini: Simplifying WiLoR into a Python package

Original repository: WiLoR, thanks to the authors for sharing

I have simplified WiLoR, focusing on the inference process. Now it can be installed via pip and used directly, and it will automatically download the model.

How to use?

  • install: pip install git+https://github.com/warmshao/WiLoR-mini
  • Usage:
import torch
import cv2
from wilor_mini.pipelines.wilor_hand_pose3d_estimation_pipeline import WiLorHandPose3dEstimationPipeline
device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
dtype = torch.float16

pipe = WiLorHandPose3dEstimationPipeline(device=device, dtype=dtype)
img_path = "assets/img.png"
image = cv2.imread(img_path)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
outputs = pipe.predict(image)

For more usage examples, please refer to: tests/test_pipelines.py

Demo

video-ff.mp4