dropout.py

from .module import Module
from .. import functional as F
from ..._jit_internal import weak_module, weak_script_method


class _DropoutNd(Module):
    __constants__ = ['p', 'inplace']

    def __init__(self, p=0.5, inplace=False):
        super(_DropoutNd, self).__init__()
        if p < 0 or p > 1:
            raise ValueError("dropout probability has to be between 0 and 1, "
                             "but got {}".format(p))
        self.p = p
        self.inplace = inplace

    def extra_repr(self):
        inplace_str = ', inplace' if self.inplace else ''
        return 'p={}{}'.format(self.p, inplace_str)


@weak_module
class Dropout(_DropoutNd):
    r"""During training, randomly zeroes some of the elements of the input
    tensor with probability :attr:`p` using samples from a Bernoulli
    distribution. Each channel will be zeroed out independently on every forward
    call.

    This has proven to be an effective technique for regularization and
    preventing the co-adaptation of neurons as described in the paper
    `Improving neural networks by preventing co-adaptation of feature
    detectors`_ .

    Furthermore, the outputs are scaled by a factor of :math:`\frac{1}{1-p}` during
    training. This means that during evaluation the module simply computes an
    identity function.

    Args:
        p: probability of an element to be zeroed. Default: 0.5
        inplace: If set to ``True``, will do this operation in-place. Default: ``False``

    Shape:
        - Input: :math:`(*)`. Input can be of any shape
        - Output: :math:`(*)`. Output is of the same shape as input

    Examples::

        >>> m = nn.Dropout(p=0.2)
        >>> input = torch.randn(20, 16)
        >>> output = m(input)

    .. _Improving neural networks by preventing co-adaptation of feature
        detectors: https://arxiv.org/abs/1207.0580
    """

    @weak_script_method
    def forward(self, input):
        return F.dropout(input, self.p, self.training, self.inplace)


@weak_module
class Dropout2d(_DropoutNd):
    r"""Randomly zero out entire channels (a channel is a 2D feature map,
    e.g., the :math:`j`-th channel of the :math:`i`-th sample in the
    batched input is a 2D tensor :math:`\text{input}[i, j]`).
    Each channel will be zeroed out independently on every forward call with
    probability :attr:`p` using samples from a Bernoulli distribution.

    Usually the input comes from :class:`nn.Conv2d` modules.

    As described in the paper
    `Efficient Object Localization Using Convolutional Networks`_ ,
    if adjacent pixels within feature maps are strongly correlated
    (as is normally the case in early convolution layers) then i.i.d. dropout
    will not regularize the activations and will otherwise just result
    in an effective learning rate decrease.

    In this case, :func:`nn.Dropout2d` will help promote independence between
    feature maps and should be used instead.

    Args:
        p (float, optional): probability of an element to be zero-ed.
        inplace (bool, optional): If set to ``True``, will do this operation
            in-place

    Shape:
        - Input: :math:`(N, C, H, W)`
        - Output: :math:`(N, C, H, W)` (same shape as input)

    Examples::

        >>> m = nn.Dropout2d(p=0.2)
        >>> input = torch.randn(20, 16, 32, 32)
        >>> output = m(input)

    .. _Efficient Object Localization Using Convolutional Networks:
       http://arxiv.org/abs/1411.4280
    """

    @weak_script_method
    def forward(self, input):
        return F.dropout2d(input, self.p, self.training, self.inplace)


@weak_module
class Dropout3d(_DropoutNd):
    r"""Randomly zero out entire channels (a channel is a 3D feature map,
    e.g., the :math:`j`-th channel of the :math:`i`-th sample in the
    batched input is a 3D tensor :math:`\text{input}[i, j]`).
    Each channel will be zeroed out independently on every forward call with
    probability :attr:`p` using samples from a Bernoulli distribution.

    Usually the input comes from :class:`nn.Conv3d` modules.

    As described in the paper
    `Efficient Object Localization Using Convolutional Networks`_ ,
    if adjacent pixels within feature maps are strongly correlated
    (as is normally the case in early convolution layers) then i.i.d. dropout
    will not regularize the activations and will otherwise just result
    in an effective learning rate decrease.

    In this case, :func:`nn.Dropout3d` will help promote independence between
    feature maps and should be used instead.

    Args:
        p (float, optional): probability of an element to be zeroed.
        inplace (bool, optional): If set to ``True``, will do this operation
            in-place

    Shape:
        - Input: :math:`(N, C, D, H, W)`
        - Output: :math:`(N, C, D, H, W)` (same shape as input)

    Examples::

        >>> m = nn.Dropout3d(p=0.2)
        >>> input = torch.randn(20, 16, 4, 32, 32)
        >>> output = m(input)

    .. _Efficient Object Localization Using Convolutional Networks:
       http://arxiv.org/abs/1411.4280
    """

    @weak_script_method
    def forward(self, input):
        return F.dropout3d(input, self.p, self.training, self.inplace)


@weak_module
class AlphaDropout(_DropoutNd):
    r"""Applies Alpha Dropout over the input.

    Alpha Dropout is a type of Dropout that maintains the self-normalizing
    property.
    For an input with zero mean and unit standard deviation, the output of
    Alpha Dropout maintains the original mean and standard deviation of the
    input.
    Alpha Dropout goes hand-in-hand with SELU activation function, which ensures
    that the outputs have zero mean and unit standard deviation.

    During training, it randomly masks some of the elements of the input
    tensor with probability *p* using samples from a bernoulli distribution.
    The elements to masked are randomized on every forward call, and scaled
    and shifted to maintain zero mean and unit standard deviation.

    During evaluation the module simply computes an identity function.

    More details can be found in the paper `Self-Normalizing Neural Networks`_ .

    Args:
        p (float): probability of an element to be dropped. Default: 0.5
        inplace (bool, optional): If set to ``True``, will do this operation
            in-place

    Shape:
        - Input: :math:`(*)`. Input can be of any shape
        - Output: :math:`(*)`. Output is of the same shape as input

    Examples::

        >>> m = nn.AlphaDropout(p=0.2)
        >>> input = torch.randn(20, 16)
        >>> output = m(input)

    .. _Self-Normalizing Neural Networks: https://arxiv.org/abs/1706.02515
    """

    @weak_script_method
    def forward(self, input):
        return F.alpha_dropout(input, self.p, self.training)


@weak_module
class FeatureAlphaDropout(_DropoutNd):

    @weak_script_method
    def forward(self, input):
        return F.feature_alpha_dropout(input, self.p, self.training)