ROMP: Monocular, One-stage, Regression of Multiple 3D People, ICCV21
Project description
Simple_ROMP
Simplified implementation of ROMP: Monocular, One-stage, Regression of Multiple 3D People, ICCV21
Please refer to https://github.com/Arthur151/ROMP for more details
Installation
pip install setuptools numpy cython
pip install simple_romp
Or install from source:
pip install setuptools numpy cython
python setup.py install
Usage
Webcam demo:
romp --mode=webcam --show
# to smooth the results, the smaller the smooth_coeff, the smoother:
romp --mode=webcam --show --temporal_optimize --smooth_coeff=3.
# to show largest person only:
romp --mode=webcam --show --temporal_optimize --smooth_coeff=3. --show_largest
Processing a single image:
romp --mode=image --show --input=/path/to/image.jpg --save_path=/path/to/output/folder/
Processing a video / a folder of images:
romp --mode=video --show --input=/path/to/video.mp4 --save_path=/path/to/output/folder/
romp --mode=video --show --input=/path/to/video_frames/ --save_path=/path/to/output/folder/
# to smooth the results, the smaller the smooth_coeff, the smoother:
romp --mode=video --show --input=/path/to/video_frames/ --save_path=/path/to/output/folder/ --temporal_optimize --smooth_coeff=3.
Copyright
Codes released under MIT license. All rights reserved by Yu Sun.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
simple_romp-0.0.2.tar.gz
(74.2 kB
view hashes)
Built Distribution
Close
Hashes for simple_romp-0.0.2-cp38-cp38-manylinux1_x86_64.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5a925a26b5cd2d8a40f031e4a7bd001f7aa1c07583e125f45e284f5f2283d58c |
|
MD5 | 9741faeab901ab6a7d02a95eb46800b4 |
|
BLAKE2b-256 | f68e5aa4e5f62a79f1a838a38976c3e84f4deb7b467a3f04a8162dd9875e18ed |