ai-agent

RankIQA.PyTorch – Quickly assess image quality for AI products

Name: RankIQA.PyTorch – Quickly assess image quality for AI products
Author: zheng-yuwei

RankIQA.PyTorch lets founders evaluate visual outputs with a PyTorch‑based IQA model, streamlining quality control for computer‑vision startups.

From the repo · “基于PyTorch实现的图像质量评估模型RankIQA”

153 stars31 forksPythonGuide quality 9/10 · reviewed Oct 10Updated 6/20/2020100% free · open source

What it does

RankIQA.PyTorch is a PyTorch-based model for evaluating the quality of images

When to use it

•When you need to assess the quality of a large number of images automatically
•When you want to compare the performance of different image processing algorithms
•When you need to filter out low-quality images from a dataset

Ready-to-paste prompt

python test.py -d /path/to/your/test/images -m models/RankIQA.pth

Heads up: Make sure you have PyTorch installed and a compatible CUDA version, as specified in the README, to avoid GPU compatibility issues

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/rankiqa-pytorch && curl -fsSL https://workflowstacks.com/api/skills/rankiqa-pytorch/claude-skill -o ~/.claude/skills/rankiqa-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 RankIQA.PyTorch – Quickly assess image quality for AI products works

Codeflow

Free to inspect

RankIQA.PyTorch – Quickly assess image quality for AI products is a medium Python project (~3.2k lines across 46 code files). Expect some technical setup — comfortable with a terminal, or ask a developer. Last commit 77 months ago, no license file, no tests found.

Size

Medium codebase

~3.2k lines · 46 code files · 27 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 99%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
main.py
Where the program starts running
3
requirements.txt
Dependencies and the commands it exposes
4
demos/__init__.py
A worked example — copy this to get going

What's in each folder

demos/Examples you can copy7 files

models/Data models & types16 files

utils/Helper scripts9 files

z_task_shell/Folder6 files

applications/Folder4 files

criterions/Folder4 files

dataloader/Folder3 files

checkpoints/Folder1 files

READMENo tests foundDocumentedNo CIExamples includedNo licenseLast update 77 mo ago