mlx.nn.init.sparse#

sparse(sparsity: float, mean: float = 0.0, std: float = 1.0, dtype: Dtype = mlx.core.float32) → Callable[[array], array]#

An initializer that returns a sparse matrix.

參數:

sparsity (float) -- The fraction of elements in each column to be set to
zero.
mean (float, optional) -- Mean of the normal distribution. Default: 0.0.
std (float, optional) -- Standard deviation of the normal distribution. Default: 1.0.
dtype (Dtype, optional) -- The data type of the array. Default: float32.

回傳值:

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

回傳值型別:

Callable[[array], array]

範例

>>> init_fn = nn.init.sparse(sparsity=0.5)
>>> init_fn(mx.zeros((2, 2)))
array([[-1.91187, -0.117483],

[0, 0]], dtype=float32)

mlx.nn.init.sparse