mindcv.models.layers

layers init

class mindcv.models.layers.Swish[source]

Bases: Cell

Swish activation function: x * sigmoid(x).

Parameters

None –

Returns

Tensor

Example

>>> x = Tensor(((20, 16), (50, 50)), mindspore.float32)
>>> Swish()(x)
construct(x)[source]

Defines the computation to be performed. This method must be overridden by all subclasses.

Note

It is not supported currently that inputs contain both tuple and non-tuple types at same time.

Parameters

  • inputs (tuple) – Tuple of variable parameters.

  • kwargs (dict) – Dictionary of variable keyword parameters.

Returns

Tensor, returns the computed result.