lightweight-human-pose-estimation.pytorch
deep-high-resolution-net.pytorch
| lightweight-human-pose-estimation.pytorch | deep-high-resolution-net.pytorch | |
|---|---|---|
| 2 | 4 | |
| 2,023 | 4,190 | |
| - | - | |
| 2.5 | 0.0 | |
| 8 days ago | over 1 year ago | |
| Python | Cuda | |
| Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lightweight-human-pose-estimation.pytorch
-
Help finding an appropriate model for human pose estimation
Lightweight OpenPose: Runs in realtime >20fps confirmed, training code is provided
-
How do I properly dissect a Github repo of a ML model?
Using https://github.com/Daniil-Osokin/lightweight-human-pose-estimation.pytorch as an example (or another repo, that was just one I found), could someone please give me a step by step process of how they read a repo for a research paper?
deep-high-resolution-net.pytorch
-
Deadlift videos needed [AI]
I am sure you have some great ideas in mind for your model design, but a quick tip (from having worked on a similar project) - it may be very challenging to simply take raw videos as input (especially with unconstrained camera viewpoints) without doing some feature extraction/keypoint detection first. For example, open-source plug-and-play 2D keypoint detectors are extremely good nowadays (e.g HRNet), and explicitly detecting 2D keypoints before classifying deadlift videos as "good" or "bad" will likely make the task more feasible!
-
[D] HRNET- Human Pose Estimation [Implementation]
The repo is well maintained on GitHub and I have replicated the author's work. But I didn't get much understanding of how things are working there. I didn't see any results.
- Help finding an appropriate model for human pose estimation
- Real time 3d reconstruction with known parameters of cameras and environment?
What are some alternatives?
BlazePose-tensorflow - A third-party Tensorflow Implementation for paper "BlazePose: On-device Real-time Body Pose tracking".
openpose - OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
mmpose - OpenMMLab Pose Estimation Toolbox and Benchmark.
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
DeepLabCut - Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
openpifpaf - Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
mediapipe - Cross-platform, customizable ML solutions for live and streaming media.
kapao - KAPAO is an efficient single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
UniPose - We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datase