tf.keras.backend.set_floatx

Sets the default float type.

tf.keras.backend.set_floatx(
    value
)

Note: It is not recommended to set this to float16 for training, as this will likely cause numeric stability issues. Instead, mixed precision, which is using a mix of float16 and float32, can be used by calling tf.keras.mixed_precision.experimental.set_policy('mixed_float16'). See the mixed precision guide for details.

Example:

tf.keras.backend.floatx()
'float32'
tf.keras.backend.set_floatx('float64')
tf.keras.backend.floatx()
'float64'
tf.keras.backend.set_floatx('float32')