Other NN Layers¶
Customized Layers¶
GramMatrix¶
Normalize¶

class
encoding.nn.
Normalize
(p=2, dim=1)[source]¶ Performs \(L_p\) normalization of inputs over specified dimension.
Does:
\[v = \frac{v}{\max(\lVert v \rVert_p, \epsilon)}\]for each subtensor v over dimension dim of input. Each subtensor is flattened into a vector, i.e. \(\lVert v \rVert_p\) is not a matrix norm.
With default arguments normalizes over the second dimension with Euclidean norm.
Parameters:
Standard Layers¶
Standard Layers as in PyTorch but in encoding.parallel.SelfDataParallel
mode. Use together with SyncBN.
Conv1d¶

class
encoding.nn.
Conv1d
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)[source]¶ Applies a 1D convolution over an input signal composed of several input planes. In the simplest case, the output value of the layer with input size \((N, C_{in}, L)\) and output \((N, C_{out}, L_{out})\) can be precisely described as:
\[\begin{array}{ll} out(N_i, C_{out_j}) = bias(C_{out_j}) + \sum_{{k}=0}^{C_{in}1} weight(C_{out_j}, k) \star input(N_i, k) \end{array}\]where \(\star\) is the valid crosscorrelation operator
stride
controls the stride for the crosscorrelation.Ifpadding
is nonzero, then the input is implicitly zeropadded on both sides forpadding
number of points.dilation
controls the spacing between the kernel points; also known as the à trous algorithm. It is harder to describe, but this link has a nice visualization of whatdilation
does.groups
controls the connections between inputs and outputs. in_channels and out_channels must both be divisible by groups.At groups=1, all inputs are convolved to all outputs.At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels, and producing half the output channels, and both subsequently concatenated. At groups=`in_channels`, each input channel is convolved with its own set of filters (of size out_channels // in_channels).Parameters:  in_channels (int) – Number of channels in the input image
 out_channels (int) – Number of channels produced by the convolution
 kernel_size (int or tuple) – Size of the convolving kernel
 stride (int or tuple, optional) – Stride of the convolution. Default: 1
 padding (int or tuple, optional) – Zeropadding added to both sides of the input. Default: 0
 dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1
 groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1
 bias (bool, optional) – If True, adds a learnable bias to the output. Default: True
 Shape:
 Input: \((N, C_{in}, L_{in})\)
 Output: \((N, C_{out}, L_{out})\) where \(L_{out} = floor((L_{in} + 2 * padding  dilation * (kernel\_size  1)  1) / stride + 1)\)
Variables:  weight (Tensor) – the learnable weights of the module of shape (out_channels, in_channels, kernel_size)
 bias (Tensor) – the learnable bias of the module of shape (out_channels)
 Examples::
>>> m = nn.Conv1d(16, 33, 3, stride=2) >>> input = autograd.Variable(torch.randn(20, 16, 50)) >>> output = m(input)
Conv2d¶

class
encoding.nn.
Conv2d
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)[source]¶ Applies a 2D convolution over an input signal composed of several input planes. In the simplest case, the output value of the layer with input size \((N, C_{in}, H, W)\) and output \((N, C_{out}, H_{out}, W_{out})\) can be precisely described as:
\[\begin{array}{ll} out(N_i, C_{out_j}) = bias(C_{out_j}) + \sum_{{k}=0}^{C_{in}1} weight(C_{out_j}, k) \star input(N_i, k) \end{array}\]where \(\star\) is the valid 2D crosscorrelation operator
stride
controls the stride for the crosscorrelation.Ifpadding
is nonzero, then the input is implicitly zeropadded on both sides forpadding
number of points.dilation
controls the spacing between the kernel points; also known as the à trous algorithm. It is harder to describe, but this link has a nice visualization of whatdilation
does.groups
controls the connections between inputs and outputs. in_channels and out_channels must both be divisible by groups.At groups=1, all inputs are convolved to all outputs.At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels, and producing half the output channels, and both subsequently concatenated. At groups=`in_channels`, each input channel is convolved with its own set of filters (of size out_channels // in_channels). The parameters
kernel_size
,stride
,padding
,dilation
can either be:  a single
int
– in which case the same value is used for the height and width dimension  a
tuple
of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension
 a single
Parameters:  in_channels (int) – Number of channels in the input image
 out_channels (int) – Number of channels produced by the convolution
 kernel_size (int or tuple) – Size of the convolving kernel
 stride (int or tuple, optional) – Stride of the convolution. Default: 1
 padding (int or tuple, optional) – Zeropadding added to both sides of the input. Default: 0
 dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1
 groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1
 bias (bool, optional) – If True, adds a learnable bias to the output. Default: True
 Shape:
 Input: \((N, C_{in}, H_{in}, W_{in})\)
 Output: \((N, C_{out}, H_{out}, W_{out})\) where \(H_{out} = floor((H_{in} + 2 * padding[0]  dilation[0] * (kernel\_size[0]  1)  1) / stride[0] + 1)\) \(W_{out} = floor((W_{in} + 2 * padding[1]  dilation[1] * (kernel\_size[1]  1)  1) / stride[1] + 1)\)
Variables:  weight (Tensor) – the learnable weights of the module of shape (out_channels, in_channels, kernel_size[0], kernel_size[1])
 bias (Tensor) – the learnable bias of the module of shape (out_channels)
 Examples::
>>> # With square kernels and equal stride >>> m = nn.Conv2d(16, 33, 3, stride=2) >>> # nonsquare kernels and unequal stride and with padding >>> m = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2)) >>> # nonsquare kernels and unequal stride and with padding and dilation >>> m = nn.Conv2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2), dilation=(3, 1)) >>> input = autograd.Variable(torch.randn(20, 16, 50, 100)) >>> output = m(input)
 The parameters
ConvTranspose2d¶

class
encoding.nn.
ConvTranspose2d
(in_channels, out_channels, kernel_size, stride=1, padding=0, output_padding=0, groups=1, bias=True, dilation=1)[source]¶ Applies a 2D transposed convolution operator over an input image composed of several input planes. This module can be seen as the gradient of Conv2d with respect to its input. It is also known as a fractionallystrided convolution or a deconvolution (although it is not an actual deconvolution operation).
stride
controls the stride for the crosscorrelation.Ifpadding
is nonzero, then the input is implicitly zeropadded on both sides forpadding
number of points.Ifoutput_padding
is nonzero, then the output is implicitly zeropadded on one side foroutput_padding
number of points.dilation
controls the spacing between the kernel points; also known as the à trous algorithm. It is harder to describe, but this link has a nice visualization of whatdilation
does.groups
controls the connections between inputs and outputs. in_channels and out_channels must both be divisible by groups.At groups=1, all inputs are convolved to all outputs.At groups=2, the operation becomes equivalent to having two conv layers side by side, each seeing half the input channels, and producing half the output channels, and both subsequently concatenated. At groups=`in_channels`, each input channel is convolved with its own set of filters (of size out_channels // in_channels). The parameters
kernel_size
,stride
,padding
,output_padding
can either be:  a single
int
– in which case the same value is used for the height and width dimensions  a
tuple
of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension
 a single
Parameters:  in_channels (int) – Number of channels in the input image
 out_channels (int) – Number of channels produced by the convolution
 kernel_size (int or tuple) – Size of the convolving kernel
 stride (int or tuple, optional) – Stride of the convolution. Default: 1
 padding (int or tuple, optional) – Zeropadding added to both sides of the input. Default: 0
 output_padding (int or tuple, optional) – Zeropadding added to one side of the output. Default: 0
 groups (int, optional) – Number of blocked connections from input channels to output channels. Default: 1
 bias (bool, optional) – If True, adds a learnable bias to the output. Default: True
 dilation (int or tuple, optional) – Spacing between kernel elements. Default: 1
 Shape:
 Input: \((N, C_{in}, H_{in}, W_{in})\)
 Output: \((N, C_{out}, H_{out}, W_{out})\) where \(H_{out} = (H_{in}  1) * stride[0]  2 * padding[0] + kernel\_size[0] + output\_padding[0]\) \(W_{out} = (W_{in}  1) * stride[1]  2 * padding[1] + kernel\_size[1] + output\_padding[1]\)
Variables:  weight (Tensor) – the learnable weights of the module of shape (in_channels, out_channels, kernel_size[0], kernel_size[1])
 bias (Tensor) – the learnable bias of the module of shape (out_channels)
 Examples::
>>> # With square kernels and equal stride >>> m = nn.ConvTranspose2d(16, 33, 3, stride=2) >>> # nonsquare kernels and unequal stride and with padding >>> m = nn.ConvTranspose2d(16, 33, (3, 5), stride=(2, 1), padding=(4, 2)) >>> input = autograd.Variable(torch.randn(20, 16, 50, 100)) >>> output = m(input) >>> # exact output size can be also specified as an argument >>> input = autograd.Variable(torch.randn(1, 16, 12, 12)) >>> downsample = nn.Conv2d(16, 16, 3, stride=2, padding=1) >>> upsample = nn.ConvTranspose2d(16, 16, 3, stride=2, padding=1) >>> h = downsample(input) >>> h.size() torch.Size([1, 16, 6, 6]) >>> output = upsample(h, output_size=input.size()) >>> output.size() torch.Size([1, 16, 12, 12])
 The parameters
ReLU¶

class
encoding.nn.
ReLU
(inplace=False)[source]¶ Applies the rectified linear unit function elementwise \({ReLU}(x)= max(0, x)\) :param inplace: can optionally do the operation inplace. Default: False
 Shape:
 Input: \((N, *)\) where * means, any number of additional dimensions
 Output: \((N, *)\), same shape as the input
 Examples::
>>> m = nn.ReLU() >>> input = autograd.Variable(torch.randn(2)) >>> print(input) >>> print(m(input))
Sigmoid¶

class
encoding.nn.
Sigmoid
[source]¶ Applies the elementwise function \(f(x) = 1 / ( 1 + exp(x))\) Shape:
 Input: \((N, *)\) where * means, any number of additional dimensions
 Output: \((N, *)\), same shape as the input
Examples:
>>> m = nn.Sigmoid() >>> input = autograd.Variable(torch.randn(2)) >>> print(input) >>> print(m(input))
MaxPool2d¶

class
encoding.nn.
MaxPool2d
(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False)[source]¶ Applies a 2D max pooling over an input signal composed of several input planes. In the simplest case, the output value of the layer with input size \((N, C, H, W)\), output \((N, C, H_{out}, W_{out})\) and
kernel_size
\((kH, kW)\) can be precisely described as:\[\begin{array}{ll} out(N_i, C_j, h, w) = \max_{{m}=0}^{kH1} \max_{{n}=0}^{kW1} input(N_i, C_j, stride[0] * h + m, stride[1] * w + n) \end{array}\]Ifpadding
is nonzero, then the input is implicitly zeropadded on both sides forpadding
number of pointsdilation
controls the spacing between the kernel points. It is harder to describe, but this link has a nice visualization of whatdilation
does. The parameters
kernel_size
,stride
,padding
,dilation
can either be:  a single
int
– in which case the same value is used for the height and width dimension  a
tuple
of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension
 a single
Parameters:  kernel_size – the size of the window to take a max over
 stride – the stride of the window. Default value is
kernel_size
 padding – implicit zero padding to be added on both sides
 dilation – a parameter that controls the stride of elements in the window
 return_indices – if True, will return the max indices along with the outputs. Useful when Unpooling later
 ceil_mode – when True, will use ceil instead of floor to compute the output shape
 Shape:
 Input: \((N, C, H_{in}, W_{in})\)
 Output: \((N, C, H_{out}, W_{out})\) where \(H_{out} = floor((H_{in} + 2 * padding[0]  dilation[0] * (kernel\_size[0]  1)  1) / stride[0] + 1)\) \(W_{out} = floor((W_{in} + 2 * padding[1]  dilation[1] * (kernel\_size[1]  1)  1) / stride[1] + 1)\)
 Examples::
>>> # pool of square window of size=3, stride=2 >>> m = nn.MaxPool2d(3, stride=2) >>> # pool of nonsquare window >>> m = nn.MaxPool2d((3, 2), stride=(2, 1)) >>> input = autograd.Variable(torch.randn(20, 16, 50, 32)) >>> output = m(input)
 The parameters
AvgPool2d¶

class
encoding.nn.
AvgPool2d
(kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True)[source]¶ Applies a 2D average pooling over an input signal composed of several input planes. In the simplest case, the output value of the layer with input size \((N, C, H, W)\), output \((N, C, H_{out}, W_{out})\) and
kernel_size
\((kH, kW)\) can be precisely described as:\[\begin{array}{ll} out(N_i, C_j, h, w) = 1 / (kH * kW) * \sum_{{m}=0}^{kH1} \sum_{{n}=0}^{kW1} input(N_i, C_j, stride[0] * h + m, stride[1] * w + n) \end{array}\]Ifpadding
is nonzero, then the input is implicitly zeropadded on both sides forpadding
number of points The parameters
kernel_size
,stride
,padding
can either be:  a single
int
– in which case the same value is used for the height and width dimension  a
tuple
of two ints – in which case, the first int is used for the height dimension, and the second int for the width dimension
 a single
Parameters:  kernel_size – the size of the window
 stride – the stride of the window. Default value is
kernel_size
 padding – implicit zero padding to be added on both sides
 ceil_mode – when True, will use ceil instead of floor to compute the output shape
 count_include_pad – when True, will include the zeropadding in the averaging calculation
 Shape:
 Input: \((N, C, H_{in}, W_{in})\)
 Output: \((N, C, H_{out}, W_{out})\) where \(H_{out} = floor((H_{in} + 2 * padding[0]  kernel\_size[0]) / stride[0] + 1)\) \(W_{out} = floor((W_{in} + 2 * padding[1]  kernel\_size[1]) / stride[1] + 1)\)
 Examples::
>>> # pool of square window of size=3, stride=2 >>> m = nn.AvgPool2d(3, stride=2) >>> # pool of nonsquare window >>> m = nn.AvgPool2d((3, 2), stride=(2, 1)) >>> input = autograd.Variable(torch.randn(20, 16, 50, 32)) >>> output = m(input)
 The parameters
AdaptiveAvgPool2d¶

class
encoding.nn.
AdaptiveAvgPool2d
(output_size)[source]¶ Applies a 2D adaptive average pooling over an input signal composed of several input planes. The output is of size H x W, for any input size. The number of output features is equal to the number of input planes.
Parameters: output_size – the target output size of the image of the form H x W. Can be a tuple (H, W) or a single number H for a square image H x H Examples
>>> # target output size of 5x7 >>> m = nn.AdaptiveAvgPool2d((5,7)) >>> input = autograd.Variable(torch.randn(1, 64, 8, 9)) >>> output = m(input) >>> # target output size of 7x7 (square) >>> m = nn.AdaptiveAvgPool2d(7) >>> input = autograd.Variable(torch.randn(1, 64, 10, 9)) >>> output = m(input)
Dropout2d¶

class
encoding.nn.
Dropout2d
(p=0.5, inplace=False)[source]¶ Randomly zeroes whole channels of the input tensor. The channels to zeroout are randomized on every forward call. Usually the input comes from 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 iid dropout will not regularize the activations and will otherwise just result in an effective learning rate decrease. In this case,
nn.Dropout2d()
will help promote independence between feature maps and should be used instead.Parameters:  Shape:
 Input: \((N, C, H, W)\)
 Output: \((N, C, H, W)\) (same shape as input)
 Examples::
>>> m = nn.Dropout2d(p=0.2) >>> input = autograd.Variable(torch.randn(20, 16, 32, 32)) >>> output = m(input)
Linear¶

class
encoding.nn.
Linear
(in_features, out_features, bias=True)[source]¶ Applies a linear transformation to the incoming data: \(y = Ax + b\)
Parameters:  in_features – size of each input sample
 out_features – size of each output sample
 bias – If set to False, the layer will not learn an additive bias. Default: True
 Shape:
 Input: \((N, *, in\_features)\) where * means any number of additional dimensions
 Output: \((N, *, out\_features)\) where all but the last dimension are the same shape as the input.
Variables:  weight – the learnable weights of the module of shape (out_features x in_features)
 bias – the learnable bias of the module of shape (out_features)
 Examples::
>>> m = nn.Linear(20, 30) >>> input = autograd.Variable(torch.randn(128, 20)) >>> output = m(input) >>> print(output.size())