🧠

Model

PoseEstimationForMobile

Name: PoseEstimationForMobile
Author: edvardHua

by edvardHua edvardhua/poseestimationformobile

Free2AITools Nexus Index

35.5

S: Semantic 50

Query-time baseline · scored live at search

A: Authority 58

P: Popularity 63

R: Recency 8

Q: Quality 70

Tech Context

Vital Performance —

Source →

Technical Constraints

Experimental / High Latency

Low FNI signal 35.5 FNI Score

Tiny - Params

- Context

0 Downloads

Commercial APACHE License

Model Information Summary
Entity Passport
Registry ID	edvardhua/poseestimationformobile
License	Apache-2.0
Provider	github

📜

Cite this model

Academic & Research Attribution

BibTeX

@misc{edvardhua_poseestimationformobile,
  author = {edvardHua},
  title = {PoseEstimationForMobile Model},
  year = {2018},
  howpublished = {\url{https://github.com/edvardHua/PoseEstimationForMobile}},
  note = {Accessed via Free2AITools.}
}

APA Style

edvardHua. (2018). PoseEstimationForMobile [Model]. Free2AITools. https://github.com/edvardHua/PoseEstimationForMobile

🔬Technical Deep Dive

Full Specifications [+]

Quick Commands

🐙 Git Clone

git clone https://github.com/edvardHua/PoseEstimationForMobile

⚖️ Free2AITools Nexus Index V2.0

Methodology How FNI works

Semantic (S) 50

Query-time baseline · scored live at search

Authority (A) 58

Popularity (P) 63

Recency (R) 8

Quality (Q) 70

💬 Index Insight

FNI V2.0 for PoseEstimationForMobile: Authority (A:58), Popularity (P:63), Recency (R:8), Quality (Q:70). Semantic (S) is a query-time baseline scored live at search.

Free2AITools Nexus Index

Data Sources / Provenance

HuggingFace API GitHub Metadata Arxiv Citation DB Methodology

Open data Updated: Live data

---

🚀 What's Next?

📊

Technical Deep Dive

This repository currently implemented the CPM and Hourglass model using TensorFlow. Instead of normal convolution, inverted residuals (also known as Mobilenet V2) module has been used inside the model for real-time inference.

Model	FLOPs	PCKh	Inference Time
CPM	0.5G	93.78	~60 FPS on Snapdragon 845 ~60 FPS on iPhone XS (need more test)
Hourglass	0.5G	91.81

You can modify the architectures of network for training much higher PCKh model.

Note: The repository only provide the baseline for mobile inference. Both model architectures (accuracy) and dataset still have a huge margin of improvement.

The respository contains:

Code of training cpm & hourglass model
Android demo source code (thanks to littleGnAl)
iOS demo source code (thanks to tucan)

Below GIF is the performance of Android and iOS

Android Mi Mix2s (~60 FPS)	iPhone X (~30 FPS)

You can download the apk as below to test on your device.

Using Mace (Support GPU)	Using TFlite (Only CPU)
PoseEstimation-Mace.apk	PoseEstimation-TFlite.apk

Issue and PR are

⚠️ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

• Benchmark scores may vary based on evaluation methodology and hardware configuration.
• VRAM requirements are estimates; actual usage depends on quantization and batch size.
• FNI scores are relative rankings and may change as new models are added.

Social Proof

GitHub Repository

1.0KStars

269Forks

Repo Issues

🐙 Data Source: GitHub ↗

🔄 Updated daily

Source summary: Based on GitHub metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseℹ️ Verify with original source

🛡️ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id: gh-model--edvardhua--poseestimationformobile
slug: edvardhua--poseestimationformobile
source: github
author: edvardHua
license: Apache-2.0
tags: pose-estimation, tensorflow, deep-neural-networks, cpm, android, ios, convolutional-neural-networks, human-pose-estimation, c++

⚙️ Technical Specs

pipeline tag: other

📊 Engagement & Metrics

downloads: 0
stars: 1,020
forks: 269

Data indexed from public sources. Updated daily.