evopose2d
openpifpaf
evopose2d | openpifpaf | |
---|---|---|
1 | 1 | |
82 | 1,129 | |
- | 0.7% | |
0.0 | 3.6 | |
over 2 years ago | 12 days ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 or later |
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.
evopose2d
-
Is there an easy way to add pose estimation into a sequential tensorflow model?
You could try EvoPose2D. It uses the TF2 Keras API. It outputs heatmaps, though, so your second network could either work with the heatmaps directly or you could try converting the heatmaps to x,y coordinates by implementing a soft argmax.
openpifpaf
-
Human Pose Estimation Recommendation
OpenPifPaf is decent, easier to install on newer systems than OpenPose imo.
What are some alternatives?
posenet-python - A Python port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)
mmpose - OpenMMLab Pose Estimation Toolbox and Benchmark.
tensorflow_Realtime_Multi-Person_Pose_Estimation - Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
metrabs - Estimate absolute 3D human poses from RGB images.
lightweight-human-pose-estimation.pytorch - Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
DECIMER-Image_Transformer - DECIMER: Deep Learning for Chemical Image Recognition using Efficient-Net V2 + Transformer
AI-basketball-analysis - :basketball::robot::basketball: AI web app and API to analyze basketball shots and shooting pose.
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.