tf.keras.backend.clear_session | TensorFlow v2.16.1 (original) (raw)

Resets all state generated by Keras.

View aliases

Main aliases

tf.keras.utils.clear_session

tf.keras.backend.clear_session(
    free_memory=True
)

Used in the notebooks

Used in the guide	Used in the tutorials
Estimators	Transfer learning for video classification with MoViNet Classifying CIFAR-10 with XLA Graph regularization for sentiment classification using synthesized graphs Graph regularization for document classification using natural graphs

Keras manages a global state, which it uses to implement the Functional model-building API and to uniquify autogenerated layer names.

If you are creating many models in a loop, this global state will consume an increasing amount of memory over time, and you may want to clear it. Calling clear_session() releases the global state: this helps avoid clutter from old models and layers, especially when memory is limited.

Args
free_memory	Whether to call Python garbage collection. It's usually a good practice to call it to make sure memory used by deleted objects is immediately freed. However, it may take a few seconds to execute, so when using clear_session() in a short loop, you may want to skip it.

Example 1: calling clear_session() when creating models in a loop

for _ in range(100):
  # Without `clear_session()`, each iteration of this loop will
  # slightly increase the size of the global state managed by Keras
  model = keras.Sequential([
      keras.layers.Dense(10) for _ in range(10)])

for _ in range(100):
  # With `clear_session()` called at the beginning,
  # Keras starts with a blank state at each iteration
  # and memory consumption is constant over time.
  keras.backend.clear_session()
  model = keras.Sequential([
      keras.layers.Dense(10) for _ in range(10)])

Example 2: resetting the layer name generation counter

layers = [keras.layers.Dense(10) for _ in range(10)] new_layer = keras.layers.Dense(10) print(new_layer.name) dense_10 keras.backend.clear_session() new_layer = keras.layers.Dense(10) print(new_layer.name) dense