ai-agent

Tianchi-2019: Automate Cloth Defect Detection

Name: Tianchi-2019: Automate Cloth Defect Detection
Author: zhengye1995

Identify fabric flaws with this solution for startup founders in manufacturing, using computer vision.

From the repo · “天池2019广东工业智造创新大赛布匹疵点检测天池水也太深了季军解决方案”

416 stars140 forksPythonGuide quality 9/10 · reviewed Aug 8Updated 5/3/2024100% free · open source

What it does

Detects cloth defects in images using a deep learning-based approach, providing a solution for the Tianchi 2019 Guangdong Intelligent Identification of Cloth Defects competition

When to use it

•When you need to automate the inspection of cloth products for defects
•When you have a large dataset of images of cloth products with defects
•When you want to improve the efficiency of your quality control process for cloth manufacturing

Ready-to-paste prompt

python test.py --image_path=/path/to/test/image --model_path=/path/to/trained/model

Heads up: The repository assumes you have a GPU with CUDA support, if you don't have a GPU, you need to modify the code to use CPU or install a GPU simulator

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/tianchi-2019-guangdong-intelligent-identification-of-cloth && curl -fsSL https://workflowstacks.com/api/skills/tianchi-2019-guangdong-intelligent-identification-of-cloth/claude-skill -o ~/.claude/skills/tianchi-2019-guangdong-intelligent-identification-of-cloth/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 Tianchi-2019: Automate Cloth Defect Detection works

Codeflow

Free to inspect

Tianchi-2019: Automate Cloth Defect Detection is a large Python project (~23k lines across 205 code files). It is a full software project: use it through its install path rather than reading it end to end. Last commit 30 months ago, no license file, has a test suite.

Size

Large codebase

~23k lines · 205 code files · ~3 h to skim

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Python

No API keys detected

Python 85%Cuda 10%C++ 5%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
requirements.txt
Dependencies and the commands it exposes
3
mmdet/core/__init__.py
Inside mmdet/core/ — the main logic begins here

What's in each folder

mmdet/core/Core code — the actual logic47 files

mmdet/models/Data models & types74 files

mmdet/ops/Deployment / infrastructure33 files

mmdet/datasets/Data files22 files

inference/Folder16 files

train/Folder9 files

temp_img/Folder6 files

mmdet/apis/Folder4 files

READMEHas testsThin docsNo CINo licenseLast update 30 mo ago