Name	Size	Mode	Actions
activation.cpython-36.pyc	47635	0644	editdlrm
adaptive.cpython-36.pyc	9725	0644	editdlrm
batchnorm.cpython-36.pyc	31039	0644	editdlrm
channelshuffle.cpython-36.pyc	1901	0644	editdlrm
container.cpython-36.pyc	27970	0644	editdlrm
conv.cpython-36.pyc	57789	0644	editdlrm
distance.cpython-36.pyc	3684	0644	editdlrm
dropout.cpython-36.pyc	10310	0644	editdlrm
flatten.cpython-36.pyc	5813	0644	editdlrm
fold.cpython-36.pyc	12807	0644	editdlrm
instancenorm.cpython-36.pyc	18808	0644	editdlrm
lazy.cpython-36.pyc	11690	0644	editdlrm
linear.cpython-36.pyc	10188	0644	editdlrm
loss.cpython-36.pyc	91465	0644	editdlrm
module.cpython-36.pyc	66530	0644	editdlrm
normalization.cpython-36.pyc	11360	0644	editdlrm
padding.cpython-36.pyc	22217	0644	editdlrm
pixelshuffle.cpython-36.pyc	4398	0644	editdlrm
pooling.cpython-36.pyc	53203	0644	editdlrm
rnn.cpython-36.pyc	44653	0644	editdlrm
sparse.cpython-36.pyc	20956	0644	editdlrm
transformer.cpython-36.pyc	20737	0644	editdlrm
upsampling.cpython-36.pyc	10780	0644	editdlrm
utils.cpython-36.pyc	2528	0644	editdlrm
_functions.cpython-36.pyc	5441	0644	editdlrm
__init__.cpython-36.pyc	5236	0644	editdlrm

3 �Eg�"�@s�dd
lm
Z

ddlmZ
ddlmZ
Gdd�de
�ZGdd �d e�ZGd d�de�Z Gdd �d e�Z Gdd�de�ZGdd�de�ZdS)�
)
�Module�)
� functional�)
�TensorcsHeZ
dZUd
dgZeedeedd��f
dd� Ze d �
d d�Z �ZS) � _DropoutNd�
p�inplace��?FN)rr �returncs<tt
|�j�
|
d
ks|
dkr,tdj|
�
�
�
|
|_||_dS)Nrr
z9dropout probability has to be between 0 and 1, but got {})�superr�__init__� ValueError�formatrr )�selfrr )
� __class__��D/usr/local/lib64/python3.6/site-packages/torch/nn/modules/dropout.pyr s





z_DropoutNd.__init__)
rc

Csd
j|j
|j�S)Nzp={}, inplace={})rrr )
rrrr� extra_reprs
z_DropoutNd.extra_repr)r F)�__name__� __module__�__qualname__Z __constants__�floatr�boolr r �strr� __classcell__rr)
rrrs


rc@s eZ
dZd
Zeed�dd�ZdS)�Dropouta�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 )�inputrcCstj
|
|j|j|j�S)
N)�
FZdropoutr�trainingr )rrrrr�forward9s
zDropout.forwardN)rrr�__doc__rr rrrrrsrc@s eZ
dZd
Zeed�dd�ZdS)� Dropout2da�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)` or :math:`(C, H, W)`. - Output: :math:`(N, C, H, W)` or :math:`(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: https://arxiv.org/abs/1411.4280 )rrcCstj
|
|j|j|j�S)
N)rZ dropout2drrr )rrrrrr cs
zDropout2d.forwardN)rrrr!rr rrrrr"=s$r"c@s eZ
dZd
Zeed�dd�ZdS)� Dropout3da�Randomly zero out entire channels (a channel is a 3D feature map, e.g., the :math:`j`-th channel of the :math:`i`-th sample in the batched input is a 3D tensor :math:`\text{input}[i, j]`). Each channel will be zeroed out independently on every forward call with probability :attr:`p` using samples from a Bernoulli distribution. Usually the input comes from :class:`nn.Conv3d` modules. As described in the paper `Efficient Object Localization Using Convolutional Networks`_ , if adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then i.i.d. dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, :func:`nn.Dropout3d` will help promote independence between feature maps and should be used instead. Args: p (float, optional): probability of an element to be zeroed. inplace (bool, optional): If set to ``True``, will do this operation in-place Shape: - Input: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)`. - Output: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` (same shape as input). Examples:: >>> m = nn.Dropout3d(p=0.2) >>> input = torch.randn(20, 16, 4, 32, 32) >>> output = m(input) .. _Efficient Object Localization Using Convolutional Networks: https://arxiv.org/abs/1411.4280 )rrcCstj
|
|j|j|j�S)
N)rZ dropout3drrr )rrrrrr �s
zDropout3d.forwardN)rrrr!rr rrrrr#gs$r#c@s eZ
dZd
Zeed�dd�ZdS)�AlphaDropouta�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 )rrcCstj
|
|j|j�S)
N)rZ alpha_dropoutrr)rrrrrr �s
zAlphaDropout.forwardN)rrrr!rr rrrrr$�s$r$c@s eZ
dZd
Zeed�dd�ZdS)�FeatureAlphaDropouta�Randomly masks out entire channels (a channel is a feature map, e.g. the :math:`j`-th channel of the :math:`i`-th sample in the batch input is a tensor :math:`\text{input}[i, j]`) of the input tensor). Instead of setting activations to zero, as in regular Dropout, the activations are set to the negative saturation value of the SELU activation function. More details can be found in the paper `Self-Normalizing Neural Networks`_ . Each element will be masked independently for each sample on every forward call with probability :attr:`p` using samples from a Bernoulli distribution. The elements to be masked are randomized on every forward call, and scaled and shifted to maintain zero mean and unit variance. Usually the input comes from :class:`nn.AlphaDropout` modules. As described in the paper `Efficient Object Localization Using Convolutional Networks`_ , if adjacent pixels within feature maps are strongly correlated (as is normally the case in early convolution layers) then i.i.d. dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case, :func:`nn.AlphaDropout` will help promote independence between feature maps and should be used instead. Args: p (float, optional): probability of an element to be zeroed. Default: 0.5 inplace (bool, optional): If set to ``True``, will do this operation in-place Shape: - Input: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)`. - Output: :math:`(N, C, D, H, W)` or :math:`(C, D, H, W)` (same shape as input). Examples:: >>> m = nn.FeatureAlphaDropout(p=0.2) >>> input = torch.randn(20, 16, 4, 32, 32) >>> output = m(input) .. _Self-Normalizing Neural Networks: https://arxiv.org/abs/1706.02515 .. _Efficient Object Localization Using Convolutional Networks: https://arxiv.org/abs/1411.4280 )rrcCstj
|
|j|j�S)
N)rZfeature_alpha_dropoutrr)rrrrrr �s
zFeatureAlphaDropout.forwardN)rrrr!rr rrrrr%�s+r%N) �moduler�rrZtorchrrrr"r#r$r%rrrr�
s
%***