tf.keras.backend.set_floatx

Set the default float dtype.

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 leverages a mix of float16 and float32. It can be configured by calling keras.mixed_precision.set_dtype_policy('mixed_float16').

Examples:

keras.config.floatx()
'float32'

keras.config.set_floatx('float64')
keras.config.floatx()
'float64'

# Set it back to float32
keras.config.set_floatx('float32')