# PaddlePaddle/PaddleClas

A treasure chest for visual classification and recognition powered by PaddlePaddle

Repository: https://github.com/PaddlePaddle/PaddleClas
Canonical: https://ross.abutalabs.com/products/paddleclas
Language: Python
License: Apache-2.0
License Family: permissive
Topics: image-classification, knowledge-distillation, autoaugment, randaugment, gridmask, cutmix, deit, repvgg, swin-transformer, pretrained-models, image-retrieval-system, image-recognition, product-recognition, fastdeploy
Last push: 2026-08-10T06:59:24+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 8, longevity 100
- inputs: {"age_days": 2347, "days_push": 23, "days_rel": 666, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5838, forks 1197 (observed 2026-08-28T04:09:31.525705+00:00)

## What it is
PaddleClas is a Python library and toolkit for image classification, recognition, and retrieval built on the PaddlePaddle deep learning framework. It ships pretrained models, training recipes, and data augmentation methods like AutoAugment, RandAugment, CutMix, and knowledge distillation.

## Use cases
- train an image classification model
- build an image retrieval system
- classify product photos
- apply knowledge distillation to vision models
- use pretrained vision transformers like Swin or DeiT
- recognize objects in images

## When to choose
- you need state-of-the-art image classification with pretrained weights
- you want an end-to-end image recognition or retrieval pipeline
- you are already using the PaddlePaddle ecosystem
- you need data augmentation and distillation recipes for vision models

## When to avoid
- your stack is PyTorch or TensorFlow based
- you need general-purpose vision tasks like detection or segmentation (use PaddleDetection/PaddleSeg)
- you want a lightweight inference-only solution without training tooling

## Facets
- artifact type: library
- maturity: active
- function: image-processing, machine-learning, deep-learning, computer-vision
- domain: computer-vision, image-processing, machine-learning, deep-learning
- platform: python
- tags: image-classification, image-retrieval, knowledge-distillation, pretrained-models, paddlepaddle, vision-transformer, product-recognition, linux, gpu

## Member repositories
- PaddlePaddle/PaddleClas (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:31.525705+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:03.245193+00:00, confidence not recorded.
  - readme: https://github.com/PaddlePaddle/PaddleClas (fetched 2026-08-28T04:09:31.525705+00:00, sha 31090b1438fb)
  - registry_pypi: https://pypi.org/pypi/paddleclas/json (fetched 2026-08-29T08:47:22.768768+00:00, sha 74f873dbc9b7)
- Data as of 2026-08-30T08:39:29.467469+00:00.