fchollet/deep-learning-models
Keras code and weights files for popular deep learning models. observed · 2026-08-28
Health v2 · maintenance only
23/100
- Activity 0
- Release rhythm 8
- Longevity 100
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.
- gap_med: n/a
- age_days: 3682
- days_rel: n/a
- days_push: 2162
- n_releases_24m: 0
Adoption not part of the score
7348 stars · 2428 forks observed · 2026-08-28
What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded
A deprecated collection of Keras code and pre-trained weights for popular deep learning image classification models such as VGG16, VGG19, ResNet50, and Inception v3. It has been superseded by the built-in keras.applications module.
Use cases
- classify images with pretrained imagenet models in keras
- extract features from images using vgg or resnet
- get intermediate layer features from pretrained networks
- load pretrained weights for vgg16 vgg19 resnet50 inception v3
- music tagging with a CRNN model
When to choose
- you are on a very old Keras setup that predates keras.applications
- you need the original standalone model files or weights for reference
When to avoid
- starting any new project - use keras.applications instead
- you need maintained code, bug fixes, or support
- you use modern TensorFlow/Keras versions
Facets
library · maturity abandoned
machine-learning deep-learning image-processing computer-vision deep-learning computer-vision image-processing machine-learning python keras pretrained-models imagenet vgg16 resnet50 inception deprecated transfer-learning
1 source
- readme: https://github.com/fchollet/deep-learning-models · fetched 2026-08-28 · 384671ac1217
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| fchollet/deep-learning-models | main | 23 |
For agents
markdown · JSON · MCP: product_card(name="fchollet/deep-learning-models")
Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem