tf.keras.backend.cast

Casts a tensor to a different dtype and returns it.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.backend.cast

tf.keras.backend.cast(
    x, dtype
)

You can cast a Keras variable but it still returns a Keras tensor.

Examples:

Cast a float32 variable to a float64 tensor

input = tf.keras.backend.ones(shape=(1,3))
print(input)
<tf.Variable 'Variable:0' shape=(1, 3) dtype=float32,
numpy=array([[1., 1., 1.]], dtype=float32)>
cast_input = tf.keras.backend.cast(input, dtype='float64')
print(cast_input)
tf.Tensor([[1. 1. 1.]], shape=(1, 3), dtype=float64)