ai-agent

MultiPoseNet.pytorch: Human Pose Estimation

Name: MultiPoseNet.pytorch: Human Pose Estimation
Author: LiMeng95

Get human pose estimation with MultiPoseNet.pytorch, a PyTorch implementation for founders building AI-powered apps.

195 stars32 forksPythonGuide quality 8/10Updated 5/23/2019100% free · open source

What it does

MultiPoseNet.pytorch estimates human poses in images or videos, allowing founders to build AI-powered apps that track and analyze human movement

When to use it

•Building a fitness app that tracks exercise form
•Developing a smart surveillance system that detects and tracks people
•Creating a gaming experience that responds to player movement

Ready-to-paste prompt

python demo.py --input ../images/test_image.jpg --output ../output --format json

Heads up: Ensure you have PyTorch 1.9 or later installed, as earlier versions may not be compatible with MultiPoseNet.pytorch

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/multiposenet-pytorch && curl -fsSL https://workflowstacks.com/api/skills/multiposenet-pytorch/claude-skill -o ~/.claude/skills/multiposenet-pytorch/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How MultiPoseNet.pytorch: Human Pose Estimation works

Codeflow

Free to inspect

MultiPoseNet.pytorch: Human Pose Estimation is a medium Python project (~4.4k lines across 51 code files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit 89 months ago, no license file, has a test suite.

Size

Medium codebase

~4.4k lines · 51 code files · 37 min skim

Setup

Some technical setup

Comfortable with a terminal? 20–40 min. Otherwise ask a dev.

Runs on

Python

No API keys detected

Python 95%C 3%Cuda 2%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
lib/__init__.py
Inside lib/ — the main logic begins here
3
demo/models/README.md
A worked example — copy this to get going

What's in each folder

lib/Core code — the actual logic22 files

demo/Examples you can copy5 files

datasets/Data files11 files

network/Folder8 files

evaluate/Folder7 files

training/Folder6 files

configs/Configuration1 files

READMEHas testsThin docsNo CIExamples includedNo licenseLast update 89 mo ago