1
1
# Keras 3: Deep Learning for Humans
2
2
3
- Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, and PyTorch .
3
+ Keras 3 is a multi-backend deep learning framework, with support for JAX, TensorFlow, PyTorch, and OpenVINO (for inference-only) .
4
4
Effortlessly build and train models for computer vision, natural language processing, audio processing,
5
5
timeseries forecasting, recommender systems, etc.
6
6
@@ -73,7 +73,7 @@ python pip_build.py --install
73
73
## Configuring your backend
74
74
75
75
You can export the environment variable ` KERAS_BACKEND ` or you can edit your local config file at ` ~/.keras/keras.json `
76
- to configure your backend. Available backend options are: ` "tensorflow" ` , ` "jax" ` , ` "torch" ` . Example:
76
+ to configure your backend. Available backend options are: ` "tensorflow" ` , ` "jax" ` , ` "torch" ` , ` "openvino" ` . Example:
77
77
78
78
```
79
79
export KERAS_BACKEND="jax"
@@ -91,6 +91,10 @@ import keras
91
91
** Note:** The backend must be configured before importing ` keras ` , and the backend cannot be changed after
92
92
the package has been imported.
93
93
94
+ ** Note:** The OpenVINO backend is an inference-only backend, meaning it is designed only for running model
95
+ predictions using ` model.predict() ` method.
96
+ To use ` openvino ` backend, install the required dependencies from the ` requirements-openvino.txt ` file.
97
+
94
98
## Backwards compatibility
95
99
96
100
Keras 3 is intended to work as a drop-in replacement for ` tf.keras ` (when using the TensorFlow backend). Just take your
0 commit comments