glorot_uniform(dtype: Dtype = mlx.core.float32) Callable[[array, float], array]#

A Glorot uniform initializer.

This initializer samples from a uniform distribution with a range computed from the number of input (fan_in) and output (fan_out) units according to:

\[\sigma = \gamma \sqrt{\frac{6.0}{\text{fan\_in} + \text{fan\_out}}}\]

For more details see the original reference: Understanding the difficulty of training deep feedforward neural networks


dtype (Dtype, optional) – The data type of the array. Default: float32.


An initializer that returns an array with the same shape as the input, filled with samples from the Glorot uniform distribution.

Return type:

Callable[[array, float], array]


>>> init_fn = nn.init.glorot_uniform()
>>> init_fn(mx.zeros((2, 2)))
array([[0.223404, -0.890597],
       [-0.379159, -0.776856]], dtype=float32)
>>> init_fn(mx.zeros((2, 2)), gain=4.0)
array([[-1.90041, 3.02264],
       [-0.912766, 4.12451]], dtype=float32)