tf.keras.models.save_model

Saves a model as a .keras file.

tf.keras.models.save_model(
    model, filepath, overwrite=True, **kwargs
)

Used in the notebooks

Used in the tutorials

modelKeras model instance to be saved.
filepathstr or pathlib.Path object. Path where to save the model.
overwriteWhether we should overwrite any existing model at the target location, or instead ask the user via an interactive prompt.

Example:

model = keras.Sequential(
    [
        keras.layers.Dense(5, input_shape=(3,)),
        keras.layers.Softmax(),
    ],
)
model.save("model.keras")
loaded_model = keras.saving.load_model("model.keras")
x = keras.random.uniform((10, 3))
assert np.allclose(model.predict(x), loaded_model.predict(x))

Note that model.save() is an alias for keras.saving.save_model().

The saved .keras file contains:

  • The model's configuration (architecture)
  • The model's weights
  • The model's optimizer's state (if any)

Thus models can be reinstantiated in the exact same state.