# qubvel/classification_models

Classification models trained on ImageNet. Keras.

Repository: https://github.com/qubvel/classification_models
Canonical: https://ross.abutalabs.com/products/classification_models
Language: Python
License: MIT
License Family: permissive
Topics: resnet, pretrained-models, pretrained-weights, keras, imagenet, imagenet-classifier, classification-model, resnext, senet, squeeze-and-excitation, inceptionv3, inception-resnet-v2, densenet, mobilenet, nasnet, xception, vgg
Last push: 2022-07-21T16:50:06+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3026, "days_push": 1504, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1231, forks 308 (observed 2026-08-28T04:04:04.192969+00:00)

## What it is
A Keras/TensorFlow Keras library providing ImageNet-pretrained image classification model architectures such as ResNet, SE-ResNet, DenseNet, MobileNet, and Inception. It is commonly used to obtain pretrained backbones for transfer learning and computer vision tasks.

## Use cases
- load imagenet pretrained resnet in keras
- get a pretrained backbone for image classification
- transfer learning with keras classification models
- compare imagenet accuracy of resnet densenet mobilenet
- use se-resnet or resnext weights in tensorflow keras
- feature extractor backbone for segmentation model

## When to choose
- you need ImageNet-pretrained classification backbones in Keras or tf.keras
- you want architectures like SE-ResNet or ResNeXt not available in keras-applications
- you are doing transfer learning or building custom vision models on top of backbones

## When to avoid
- you use PyTorch instead of Keras/TensorFlow
- you need the latest architectures or actively maintained releases
- you need models beyond ImageNet classification, such as detection heads

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing
- domain: deep-learning, computer-vision, image-processing
- platform: python
- tags: keras, tensorflow, imagenet, pretrained-weights, resnet, densenet, mobilenet, image-classification, backbone

## Member repositories
- qubvel/classification_models (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:04.192969+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 2026-08-30T08:22:31.367842+00:00, confidence not recorded.
  - readme: https://github.com/qubvel/classification_models (fetched 2026-08-28T04:04:04.192969+00:00, sha 106e0325ae9c)
- Data as of 2026-08-30T08:39:29.467469+00:00.