Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Deep Learning for humans
| Date | Stars |
|---|---|
| 2026-07-31 | 64189 |
| 2026-08-06 | 64225 |
| 2026-08-07 | 64221 |
| 2026-08-08 | 64222 |
| 2026-08-09 | 64221 |
| 2026-08-10 | 64223 |
| 2026-08-11 | 64224 |
| 2026-08-12 | 64226 |
| 2026-08-13 | 64230 |
| 2026-08-14 | 64229 |
| 2026-08-15 | 64230 |
| 2026-08-16 | 64233 |
| 2026-08-17 | 64233 |
| 2026-08-18 | 64238 |
| 2026-08-19 | 64241 |
| 2026-08-20 | 64240 |
| 2026-08-21 | 64240 |
| 2026-08-22 | 64245 |
| 2026-08-23 | 64249 |
| 2026-08-24 | 64248 |
| 2026-08-25 | 64249 |
| 2026-08-26 | 64250 |
| 2026-08-27 | 64255 |
| 2026-08-28 | 64260 |
| 2026-08-29 | 64268 |
| 2026-08-30 | 64269 |
| 2026-08-31 | 64271 |
| 2026-09-01 | 64269 |
| 2026-09-02 | 64271 |
| 2026-09-03 | 64275 |
| 2026-09-04 | 64275 |
| 2026-09-05 | 64279 |
| 2026-09-06 | 64303 |
| 2026-09-07 | 64320 |
| 2026-09-08 | 64319 |
| 2026-09-09 | 64321 |
| 2026-09-10 | 64317 |
| 2026-09-11 | 64317 |
| 2026-09-12 | 64317 |
| 2026-09-13 | 64319 |
| 2026-09-14 | 64321 |
| 2026-09-15 | 64320 |
| 2026-09-16 | 64317 |
| 2026-09-17 | 64318 |
| 2026-09-18 | 64320 |
| 2026-09-19 | 64321 |
| 2026-09-20 | 64322 |
| 2026-09-21 | 64324 |
| 2026-09-22 | 64328 |
| 2026-09-23 | 64332 |
| 2026-09-24 | 64334 |
| 2026-09-25 | 64341 |
| 2026-09-26 | 64343 |
| 2026-09-27 | 64346 |
| 2026-09-28 | 64346 |
| 2026-09-29 | 64344 |
| 2026-09-30 | 64343 |
| 2026-10-01 | 64343 |
| 2026-10-02 | 64347 |
| 2026-10-03 | 64348 |
| 2026-10-04 | 64349 |
| 2026-10-05 | 64353 |
| 2026-10-06 | 64354 |
| 2026-10-07 | 64350 |
| 2026-10-08 | 64353 |
| 2026-10-09 | 64354 |
| 2026-10-10 | 64360 |
| 2026-10-11 | 64364 |
| 2026-10-12 | 64364 |
| 2026-10-13 | 64372 |
| 2026-10-14 | 64372 |
| 2026-10-15 | 64373 |
| 2026-10-16 | 64374 |
| 2026-10-17 | 64378 |
| 2026-10-18 | 64374 |
| 2026-10-19 | 64373 |
| 2026-10-20 | 64374 |
| 2026-10-21 | 64377 |
| 2026-10-22 | 64377 |
| 2026-10-23 | 64377 |
| 2026-10-24 | 64381 |
| 2026-10-25 | 64388 |
| 2026-10-26 | 64390 |
| 2026-10-27 | 64391 |
| 2026-10-28 | 64391 |
| 2026-10-29 | 64397 |
| 2026-10-30 | 64397 |
| 2026-10-31 | 64405 |
| 2026-11-01 | 64409 |
| 2026-11-02 | 64412 |
| 2026-11-03 | 64413 |
| 2026-11-04 | 64417 |
Today
+4 stars today
This week
+26 stars this week
This month
+64 stars this month
Momentum
47.0
growth rate 0.04%/day
# Keras 3: Deep Learning for Humans
Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO (for inference-only).
Effortlessly build and train models for computer vision, natural language processing, audio processing,
timeseries forecasting, recommender systems, etc.
- **Accelerated model development**: Ship deep learning solutions faster thanks to the high-level UX of Keras
and the availability of easy-to-debug runtimes like PyTorch or JAX eager execution.
- **State-of-the-art performance**: By picking the backend that is the fastest for your model architecture (often JAX!),
leverage speedups ranging from 20% to 350% compared to other frameworks. [Benchmark here](https://keras.io/getting_started/benchmarks/).
- **Datacenter-scale training**: Scale confidently from your laptop to large clusters of GPUs or TPUs.
Join nearly three million developers, from burgeoning startups to global enterprises, in harnessing the power of Keras 3.
## Installation
### Install with pip
Keras 3 is available on PyPI as `keras`. Note that Keras 2 remains available as the `tf-keras` package.
1. Install `keras`:
```
pip install keras --upgrade
```
2. Install backend package(s).
To use `keras`, you should also install the backend of choice: `tensorflow`, `jax`, or `torch`. Additionally,
The `openvino` backend is available with support for model inference only.
3. (Optional) Install remote file access support.
To save to and load from Google Cloud Storage (`gs://` paths) without TensorFlow, install the `gcs` extra:
```
pip install "keras[gcs]"
```
### Local installation
#### Minimal installation
Keras 3 is compatible with Linux and macOS systems. For Windows users, we recommend using WSL2 to run Keras.
To install a local development version:
1. Install dependencies:
```
pip install -r requirements.txt
```
2. Run installation command from the root directory.
```
python pip_build.py --install
```
3. Run API generation script when creating PRs that update `keras_export` public APIs:
```
./shell/api_gen.sh
```
## Backend Compatibility Table
The following table lists the minimum supported versions of each backend for the latest stable release of Keras (v3.x):
| Backend | Minimum Supported Version |
|------------|---------------------------|
| TensorFlow | 2.16.1 |
| JAX | 0.4.20 |
| PyTorch | 2.6.0 |
| OpenVINO | 2026.2.0 |
#### Adding GPU support
The `requirements.txt` file will install a CPU-only version of TensorFlow, JAX, and PyTorch. For GPU support, we also
provide a separate `requirements-{backend}-cuda.txt` for TensorFlow, JAX, and PyTorch. These install all CUDA
dependencies via `pip` and expect a NVIDIA driver to be pre-installed. We recommend a clean Python environment for each
backend to avoid CUDA version mismatches. As an example, here is how to create a JAX GPU environment with `conda`:
```shell
conda create -y -n keras-jax python=3.10
conda activate keras-jax
pip install -r requirements-jax-cuda.txt
python pip_build.py --install
```
## Configuring your backend
You can export the environment variable `KERAS_BACKEND` or you can edit your local config file at `~/.keras/keras.json`
to configure your backend. Available backend options are: `"tensorflow"`, `"jax"`, `"torch"`, `"openvino"`. Example:
```
export KERAS_BACKEND="jax"
```
In Colab, you can do:
```python
import os
os.environ["KERAS_BACKEND"] = "jax"
import keras
```
**Note:** The backend must be configured before importing `keras`, and the backend cannot be changed after
the package has been imported.
**Note:** The OpenVINO backend is an inference-only backend, meaning it is designed only for running model
predictions using `model.predict()` method.
## Backwards compatibility
Keras 3 is intended to work as a drop-in replacement for `tf.keras` (when using the TensorFlow backend). Just take your
existing `tf.kerExcerpt of 5,547 characters
Read on GitHub
François Chollet
3.9k
TensorFlower Gardener
572
Qianli Scott Zhu · Google · United States
422
411
Hongyu, Chiu · Taiwan
231
Haifeng Jin
211
Fariz Rahman · India
209
Matt Watson · Google · United States
207
Chen Qian · United States
189
Taehoon Lee · @Desilo · South Korea
164
Gabriel de Marmiesse · Kyutai · France
127
Ugeun Park · Samsung Electronics · South Korea
125
Ramesh Sampath · United States
115
Divyashree Sreepathihalli · Google
114
Neel Kovelamudi · Google · United States
114
Samuel Marks · @offscale
111
Oleg Zabluda · United States
107
Aditya Goyal · India
98
Kaan Bıçakcı · WTW · United Kingdom
81
Rick Chao
75
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:13634be7177d4fba, topic:deep-learning, topic:pytorch, topic:tensorflow