jax.nn.initializers.delta_orthogonal#

jax.nn.initializers.delta_orthogonal(scale=1.0, column_axis=-1, dtype=<class 'jax.numpy.float64'>)[source]#

Builds an initializer for delta orthogonal kernels.

Parameters:

  • scale (RealNumeric) – the upper bound of the uniform distribution.

  • column_axis (int) – the axis that contains the columns that should be orthogonal.

  • dtype (DTypeLikeInexact) – the default dtype of the weights.

Returns:

A delta orthogonal initializer. The shape passed to the initializer must be 3D, 4D, or 5D.

Return type:

Initializer

Examples:

>>> import jax, jax.numpy as jnp
>>> initializer = jax.nn.initializers.delta_orthogonal()
>>> initializer(jax.random.key(42), (3, 3, 3), jnp.float32)  
Array([[[ 0.        ,  0.        ,  0.        ],
        [ 0.        ,  0.        ,  0.        ],
        [ 0.        ,  0.        ,  0.        ]],

       [[ 0.27858758, -0.7949833 , -0.53887904],
        [ 0.9120717 ,  0.04322892,  0.40774566],
        [-0.30085585, -0.6050892 ,  0.73712474]],

       [[ 0.        ,  0.        ,  0.        ],
        [ 0.        ,  0.        ,  0.        ],
        [ 0.        ,  0.        ,  0.        ]]], dtype=float32)