# Layers¶

## Data layer¶

### data¶

paddle.v2.layer.data

name 的别名

## Fully Connected Layers¶

### fc¶

class paddle.v2.layer.fc

Helper for declare fully connected layer.

The example usage is:

fc = fc(input=layer,
size=1024,
bias_attr=False)


which is equal to:

with mixed(size=1024) as fc:
fc += full_matrix_projection(input=layer)

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer|list|tuple) – The input layer. Could be a list/tuple of input layer. size (int) – The layer dimension. act (paddle.v2.activation.Base) – Activation Type. Default is tanh. param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute|list. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### selective_fc¶

class paddle.v2.layer.selective_fc

Selectived fully connected layer. Different from fc, the output of this layer maybe sparse. It requires an additional input to indicate several selected columns for output. If the selected columns is not specified, selective_fc acts exactly like fc.

The simple usage is:

sel_fc = selective_fc(input=input, size=128, act=paddle.v2.activation.Tanh())

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer|list|tuple) – The input layer. select (paddle.v2.config_base.Layer) – The select layer. The output of select layer should be a sparse binary matrix, and treat as the mask of selective fc. If is None, acts exactly like fc. size (int) – The layer dimension. act (paddle.v2.activation.Base) – Activation Type. Default is tanh. param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Conv Layers¶

### conv_operator¶

class paddle.v2.layer.conv_operator

Different from img_conv, conv_op is an Operator, which can be used in mixed. And conv_op takes two inputs to perform convolution. The first input is the image and the second is filter kernel. It only support GPU mode.

The example usage is:

op = conv_operator(img=input1,
filter=input2,
filter_size=3,
num_filters=64,
num_channels=64)

参数: img (paddle.v2.config_base.Layer) – input image filter (paddle.v2.config_base.Layer) – input filter filter_size (int) – The x dimension of a filter kernel. filter_size_y (int) – The y dimension of a filter kernel. Since PaddlePaddle now supports rectangular filters, the filter’s shape can be (filter_size, filter_size_y). num_filters (int) – channel of output data. num_channels (int) – channel of input data. stride (int) – The x dimension of the stride. stride_y (int) – The y dimension of the stride. padding (int) – The x dimension of padding. padding_y (int) – The y dimension of padding. A ConvOperator Object. ConvOperator

### conv_projection¶

class paddle.v2.layer.conv_projection

Different from img_conv and conv_op, conv_projection is an Projection, which can be used in mixed and conat. It use cudnn to implement conv and only support GPU mode.

The example usage is:

proj = conv_projection(input=input1,
filter_size=3,
num_filters=64,
num_channels=64)

参数: input (paddle.v2.config_base.Layer) – input layer filter_size (int) – The x dimension of a filter kernel. filter_size_y (int) – The y dimension of a filter kernel. Since PaddlePaddle now supports rectangular filters, the filter’s shape can be (filter_size, filter_size_y). num_filters (int) – channel of output data. num_channels (int) – channel of input data. stride (int) – The x dimension of the stride. stride_y (int) – The y dimension of the stride. padding (int) – The x dimension of padding. padding_y (int) – The y dimension of padding. groups (int) – The group number. param_attr (paddle.v2.attr.ParameterAttribute) – Convolution param attribute. None means default attribute trans (boolean) – whether it is convTrans or conv A DotMulProjection Object. DotMulProjection

### conv_shift¶

class paddle.v2.layer.conv_shift
This layer performs cyclic convolution for two input. For example:
• a[in]: contains M elements.
• b[in]: contains N elements (N should be odd).
• c[out]: contains M elements.
$c[i] = \sum_{j=-(N-1)/2}^{(N-1)/2}a_{i+j} * b_{j}$
In this formular:
• a’s index is computed modulo M. When it is negative, then get item from the right side (which is the end of array) to the left.
• b’s index is computed modulo N. When it is negative, then get item from the right size (which is the end of array) to the left.

The example usage is:

conv_shift = conv_shift(a=layer1, b=layer2)

参数: name (basestring) – The name of this layer. It is optional. a (paddle.v2.config_base.Layer) – Input layer a. b (paddle.v2.config_base.Layer) – input layer b. layer_attr (paddle.v2.attr.ExtraAttribute) – layer’s extra attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### img_conv¶

class paddle.v2.layer.img_conv

Convolution layer for image. Paddle can support both square and non-square input currently.

The details of convolution layer, please refer UFLDL’s convolution .

Convolution Transpose (deconv) layer for image. Paddle can support both square and non-square input currently.

The details of convolution transpose layer, please refer to the following explanation and references therein <http://datascience.stackexchange.com/questions/6107/ what-are-deconvolutional-layers/>_ . The num_channel means input image’s channel number. It may be 1 or 3 when input is raw pixels of image(mono or RGB), or it may be the previous layer’s num_filters * num_group.

There are several group of filter in PaddlePaddle implementation. Each group will process some channel of the inputs. For example, if an input num_channel = 256, group = 4, num_filter=32, the PaddlePaddle will create 32*4 = 128 filters to process inputs. The channels will be split into 4 pieces. First 256/4 = 64 channels will process by first 32 filters. The rest channels will be processed by rest group of filters.

The example usage is:

conv = img_conv(input=data, filter_size=1, filter_size_y=1,
num_channels=8,
num_filters=16, stride=1,
bias_attr=False,


### context_projection¶

class paddle.v2.layer.context_projection

Context Projection.

It just simply reorganizes input sequence, combines “context_len” sequence to one context from context_start. “context_start” will be set to -(context_len - 1) / 2 by default. If context position out of sequence length, padding will be filled as zero if padding_attr = False, otherwise it is trainable.

For example, origin sequence is [A B C D E F G], context len is 3, then after context projection and not set padding_attr, sequence will be [ 0AB ABC BCD CDE DEF EFG FG0 ].

参数: input (paddle.v2.config_base.Layer) – Input Sequence. context_len (int) – context length. context_start (int) – context start position. Default is -(context_len - 1)/2 padding_attr (bool|paddle.v2.attr.ParameterAttribute) – Padding Parameter Attribute. If false, it means padding always be zero. Otherwise Padding is learnable, and parameter attribute is set by this parameter. Projection Projection

### row_conv¶

class paddle.v2.layer.row_conv

The row convolution is called lookahead convolution. It is firstly introduced in paper of Deep Speech 2: End-to-End Speech Recognition in English and Mandarin .

The bidirectional RNN that learns representation for a sequence by performing a forward and a backward pass through the entire sequence. However, unlike unidirectional RNNs, bidirectional RNNs are challenging to deploy in an online and low-latency setting. The lookahead convolution incorporates information from future subsequences in a computationally efficient manner to improve unidirectional RNNs.

The connection of row convolution is different from the 1D sequence convolution. Assumed that, the future context-length is k, that is to say, it can get the output at timestep t by using the the input feature from t-th timestep to (t+k+1)-th timestep. Assumed that the hidden dim of input activations are d, the activations r_t for the new layer at time-step t are:

$r_{t,r} = \sum_{j=1}^{k + 1} {w_{i,j}h_{t+j-1, i}} \quad ext{for} \quad (1 \leq i \leq d)$

The context_len is k + 1. That is to say, the lookahead step number plus one equals context_len.

row_conv = row_conv(input=input, context_len=3)

参数: input (paddle.v2.config_base.Layer) – The input layer. context_len (int) – The context length equals the lookahead step number plus one. act (paddle.v2.activation.Base) – Activation Type. Default is linear activation. param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute. If None, the parameter will be initialized smartly. It’s better to set it by yourself. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Image Pooling Layer¶

### img_pool¶

class paddle.v2.layer.img_pool

Image pooling Layer.

The details of pooling layer, please refer ufldl’s pooling .

• ceil_mode=True:
$w = 1 + int(ceil(input\_width + 2 * padding - pool\_size) / float(stride)) h = 1 + int(ceil(input\_height + 2 * padding\_y - pool\_size\_y) / float(stride\_y))$
• ceil_mode=False:
$w = 1 + int(floor(input\_width + 2 * padding - pool\_size) / float(stride)) h = 1 + int(floor(input\_height + 2 * padding\_y - pool\_size\_y) / float(stride\_y))$

The example usage is:

maxpool = img_pool(input=conv,
pool_size=3,
pool_size_y=5,
num_channels=8,
stride=1,
stride_y=2,
pool_type=MaxPooling())

参数: padding (int) – pooling padding width. padding_y (int|None) – pooling padding height. It’s equal to padding by default. name (basestring.) – name of pooling layer input (paddle.v2.config_base.Layer) – layer’s input pool_size (int) – pooling window width pool_size_y (int|None) – pooling window height. It’s eaqual to pool_size by default. num_channels (int) – number of input channel. pool_type (BasePoolingType) – pooling type. MaxPooling or AvgPooling. Default is MaxPooling. stride (int) – stride width of pooling. stride_y (int|None) – stride height of pooling. It is equal to stride by default. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer attribute. ceil_mode (bool) – Wether to use ceil mode to calculate output height and with. Defalut is True. If set false, Otherwise use floor. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### spp¶

class paddle.v2.layer.spp

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. The details please refer to Kaiming He’s paper.

The example usage is:

spp = spp(input=data,
pyramid_height=2,
num_channels=16,
pool_type=MaxPooling())

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – layer’s input. num_channels (int) – number of input channel. pool_type – Pooling type. MaxPooling or AveragePooling. Default is MaxPooling. pyramid_height (int) – pyramid height. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### maxout¶

class paddle.v2.layer.maxout
A layer to do max out on conv layer output.
• Input: output of a conv layer.
• Output: feature map size same as input. Channel is (input channel) / groups.

So groups should be larger than 1, and the num of channels should be able to devided by groups.

$y_{si+j} = \max_k x_{gsi + sk + j} g = groups s = input.size / num_channels 0 \le i < num_channels / groups 0 \le j < s 0 \le k < groups$

The simple usage is:

maxout = maxout(input,
num_channels=128,
groups=4)

参数: input (paddle.v2.config_base.Layer) – The input layer. num_channels (int|None) – The channel number of input layer. If None will be set automatically from previous output. groups (int) – The group number of input layer. name (None|basestring.) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Norm Layer¶

### img_cmrnorm¶

class paddle.v2.layer.img_cmrnorm

Response normalization across feature maps. The details please refer to Alex’s paper.

The example usage is:

norm = img_cmrnorm(input=net, size=5)

参数: name (None|basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – layer’s input. size (int) – Normalize in number of $$size$$ feature maps. scale (float) – The hyper-parameter. power (float) – The hyper-parameter. num_channels – input layer’s filers number or channels. If num_channels is None, it will be set automatically. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### batch_norm¶

class paddle.v2.layer.batch_norm

Batch Normalization Layer. The notation of this layer as follow.

$$x$$ is the input features over a mini-batch.

$\begin{split}\mu_{\beta} &\gets \frac{1}{m} \sum_{i=1}^{m} x_i \qquad &//\ \ mini-batch\ mean \\ \sigma_{\beta}^{2} &\gets \frac{1}{m} \sum_{i=1}^{m}(x_i - \ \mu_{\beta})^2 \qquad &//\ mini-batch\ variance \\ \hat{x_i} &\gets \frac{x_i - \mu_\beta} {\sqrt{\ \sigma_{\beta}^{2} + \epsilon}} \qquad &//\ normalize \\ y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift\end{split}$

The details of batch normalization please refer to this paper.

The example usage is:

norm = batch_norm(input=net, act=paddle.v2.activation.Relu())

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – batch normalization input. Better be linear activation. Because there is an activation inside batch_normalization. batch_norm_type (None|string, None or "batch_norm" or "cudnn_batch_norm") – We have batch_norm and cudnn_batch_norm. batch_norm supports both CPU and GPU. cudnn_batch_norm requires cuDNN version greater or equal to v4 (>=v4). But cudnn_batch_norm is faster and needs less memory than batch_norm. By default (None), we will automaticly select cudnn_batch_norm for GPU and batch_norm for CPU. Otherwise, select batch norm type based on the specified type. If you use cudnn_batch_norm, we suggested you use latest version, such as v5.1. act (paddle.v2.activation.Base) – Activation Type. Better be relu. Because batch normalization will normalize input near zero. num_channels (int) – num of image channels or previous layer’s number of filters. None will automatically get from layer’s input. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – $$\beta$$, better be zero when initialize. So the initial_std=0, initial_mean=1 is best practice. param_attr (paddle.v2.attr.ParameterAttribute) – $$\gamma$$, better be one when initialize. So the initial_std=0, initial_mean=1 is best practice. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. use_global_stats (bool|None.) – whether use moving mean/variance statistics during testing peroid. If None or True, it will use moving mean/variance statistics during testing. If False, it will use the mean and variance of current batch of test data for testing. moving_average_fraction (float.) – Factor used in the moving average computation, referred to as facotr, $$runningMean = newMean*(1-factor) + runningMean*factor$$ mean_var_names (string list) – [mean name, variance name] paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### sum_to_one_norm¶

class paddle.v2.layer.sum_to_one_norm

A layer for sum-to-one normalization, which is used in NEURAL TURING MACHINE.

$out[i] = \frac {in[i]} {\sum_{k=1}^N in[k]}$

where $$in$$ is a (batchSize x dataDim) input vector, and $$out$$ is a (batchSize x dataDim) output vector.

The example usage is:

sum_to_one_norm = sum_to_one_norm(input=layer)

参数: input (paddle.v2.config_base.Layer) – Input layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### cross_channel_norm¶

class paddle.v2.layer.cross_channel_norm

Normalize a layer’s output. This layer is necessary for ssd. This layer applys normalize across the channels of each sample to a conv layer’s output and scale the output by a group of trainable factors which dimensions equal to the channel’s number.

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – The input layer. param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute|list. paddle.v2.config_base.Layer

### row_l2_norm¶

class paddle.v2.layer.row_l2_norm

A layer for L2-normalization in each row.

$out[i] =$

rac{in[i]}{sqrt{sum_{k=1}^N in[k]^{2}}}

where the size of $$in$$ is (batchSize x dataDim) , and the size of $$out$$ is a (batchSize x dataDim) .

The example usage is:

row_l2_norm = row_l2_norm(input=layer)

param input: type input: Input layer. paddle.v2.config_base.Layer The name of this layer. It is optional. basestring extra layer attributes. paddle.v2.attr.ExtraAttribute paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Recurrent Layers¶

### recurrent¶

class paddle.v2.layer.recurrent

Simple recurrent unit layer. It is just a fully connect layer through both time and neural network.

For each sequence [start, end] it performs the following computation:

$\begin{split}out_{i} = act(in_{i}) \ \ \text{for} \ i = start \\ out_{i} = act(in_{i} + out_{i-1} * W) \ \ \text{for} \ start < i <= end\end{split}$

If reversed is true, the order is reversed:

$\begin{split}out_{i} = act(in_{i}) \ \ \text{for} \ i = end \\ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start <= i < end\end{split}$
参数: input (paddle.v2.config_base.Layer) – Input Layer act (paddle.v2.activation.Base) – activation. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. param_attr (paddle.v2.attr.ParameterAttribute) – parameter attribute. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### lstmemory¶

class paddle.v2.layer.lstmemory

Long Short-term Memory Cell.

The memory cell was implemented as follow equations.

\begin{align}\begin{aligned}i_t & = \sigma(W_{xi}x_{t} + W_{hi}h_{t-1} + W_{ci}c_{t-1} + b_i)\\f_t & = \sigma(W_{xf}x_{t} + W_{hf}h_{t-1} + W_{cf}c_{t-1} + b_f)\\c_t & = f_tc_{t-1} + i_t tanh (W_{xc}x_t+W_{hc}h_{t-1} + b_c)\\o_t & = \sigma(W_{xo}x_{t} + W_{ho}h_{t-1} + W_{co}c_t + b_o)\\h_t & = o_t tanh(c_t)\end{aligned}\end{align}

NOTE: In PaddlePaddle’s implementation, the multiplications $$W_{xi}x_{t}$$ , $$W_{xf}x_{t}$$, $$W_{xc}x_t$$, $$W_{xo}x_{t}$$ are not done in the lstmemory layer, so an additional mixed with full_matrix_projection or a fc must be included in the configuration file to complete the input-to-hidden mappings before lstmemory is called.

NOTE: This is a low level user interface. You can use network.simple_lstm to config a simple plain lstm layer.

Please refer to Generating Sequences With Recurrent Neural Networks for more details about LSTM.

参数: name (basestring) – The lstmemory layer name. size (int) – DEPRECATED. size of the lstm cell input (paddle.v2.config_base.Layer) – input layer name. reverse (bool) – is sequence process reversed or not. act (paddle.v2.activation.Base) – activation type, paddle.v2.activation.Tanh by default. $$h_t$$ gate_act (paddle.v2.activation.Base) – gate activation type, paddle.v2.activation.Sigmoid by default. state_act (paddle.v2.activation.Base) – state activation type, paddle.v2.activation.Tanh by default. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. param_attr (paddle.v2.attr.ParameterAttribute|None|False) – Parameter Attribute. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer attribute paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### grumemory¶

class paddle.v2.layer.grumemory

Gate Recurrent Unit Layer.

The memory cell was implemented as follow equations.

1. update gate $$z$$: defines how much of the previous memory to keep around or the unit updates its activations. The update gate is computed by:

$z_t = \sigma(W_{z}x_{t} + U_{z}h_{t-1} + b_z)$

2. reset gate $$r$$: determines how to combine the new input with the previous memory. The reset gate is computed similarly to the update gate:

$r_t = \sigma(W_{r}x_{t} + U_{r}h_{t-1} + b_r)$

3. The candidate activation $$\tilde{h_t}$$ is computed similarly to that of the traditional recurrent unit:

${\tilde{h_t}} = tanh(W x_{t} + U (r_{t} \odot h_{t-1}) + b)$

4. The hidden activation $$h_t$$ of the GRU at time t is a linear interpolation between the previous activation $$h_{t-1}$$ and the candidate activation $$\tilde{h_t}$$:

$h_t = (1 - z_t) h_{t-1} + z_t {\tilde{h_t}}$

NOTE: In PaddlePaddle’s implementation, the multiplication operations $$W_{r}x_{t}$$, $$W_{z}x_{t}$$ and $$W x_t$$ are not computed in gate_recurrent layer. Consequently, an additional mixed with full_matrix_projection or a fc must be included before grumemory is called.

More details can be found by referring to Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling.

The simple usage is:

gru = grumemory(input)

参数: name (None|basestring) – The gru layer name. input (paddle.v2.config_base.Layer.) – input layer. size (int) – DEPRECATED. size of the gru cell reverse (bool) – Whether sequence process is reversed or not. act (paddle.v2.activation.Base) – activation type, paddle.v2.activation.Tanh by default. This activation affects the $${\tilde{h_t}}$$. gate_act (paddle.v2.activation.Base) – gate activation type, paddle.v2.activation.Sigmoid by default. This activation affects the $$z_t$$ and $$r_t$$. It is the $$\sigma$$ in the above formula. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. param_attr (paddle.v2.attr.ParameterAttribute|None|False) – Parameter Attribute. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer attribute paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Recurrent Layer Group¶

### memory¶

class paddle.v2.layer.memory

The memory layers is a layer cross each time step. Reference this output as previous time step layer name ‘s output.

The default memory is zero in first time step, previous time step’s output in the rest time steps.

If boot_bias, the first time step value is this bias and with activation.

If boot_with_const_id, then the first time stop is a IndexSlot, the Arguments.ids()[0] is this cost_id.

If boot is not null, the memory is just the boot’s output. Set is_seq is true boot layer is sequence.

The same name layer in recurrent group will set memory on each time step.

mem = memory(size=256, name='state')
state = fc(input=mem, size=256, name='state')


If you do not want to specify the name, you can equivalently use set_input() to specify the layer needs to be remembered as the following:

mem = memory(size=256)
state = fc(input=mem, size=256)
mem.set_input(mem)

参数: name (basestring) – the name of the layer which this memory remembers. If name is None, user should call set_input() to specify the name of the layer which this memory remembers. size (int) – size of memory. memory_name (basestring) – the name of the memory. It is ignored when name is provided. is_seq (bool) – DEPRECATED. is sequence for boot boot (paddle.v2.config_base.Layer|None) – boot layer of memory. boot_bias (paddle.v2.attr.ParameterAttribute|None) – boot layer’s bias boot_bias_active_type (paddle.v2.activation.Base) – boot layer’s active type. boot_with_const_id (int) – boot layer’s id. paddle.v2.config_base.Layer object which is a memory. paddle.v2.config_base.Layer

### recurrent_group¶

class paddle.v2.layer.recurrent_group

Recurrent layer group is an extremely flexible recurrent unit in PaddlePaddle. As long as the user defines the calculation done within a time step, PaddlePaddle will iterate such a recurrent calculation over sequence input. This is extremely usefull for attention based model, or Neural Turning Machine like models.

The basic usage (time steps) is:

def step(input):
output = fc(input=layer,
size=1024,
bias_attr=False)
return output

group = recurrent_group(input=layer,
step=step)


You can see following configs for further usages:

• time steps: lstmemory_group, paddle/gserver/tests/sequence_group.conf, demo/seqToseq/seqToseq_net.py
参数: step (callable) – recurrent one time step function.The input of this function is input of the group. The return of this function will be recurrent group’s return value. The recurrent group scatter a sequence into time steps. And for each time step, will invoke step function, and return a time step result. Then gather each time step of output into layer group’s output. name (basestring) – recurrent_group’s name. input (paddle.v2.config_base.Layer|StaticInput|SubsequenceInput|list|tuple) – Input links array. paddle.v2.config_base.Layer will be scattered into time steps. SubsequenceInput will be scattered into sequence steps. StaticInput will be imported to each time step, and doesn’t change through time. It’s a mechanism to access layer outside step function. reverse (bool) – If reverse is set true, the recurrent unit will process the input sequence in a reverse order. targetInlink (paddle.v2.config_base.Layer|SubsequenceInput) – DEPRECATED. The input layer which share info with layer group’s output Param input specifies multiple input layers. For SubsequenceInput inputs, config should assign one input layer that share info(the number of sentences and the number of words in each sentence) with all layer group’s outputs. targetInlink should be one of the layer group’s input. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### lstm_step¶

class paddle.v2.layer.lstm_step

LSTM Step Layer. This function is used only in recurrent_group. The lstm equations are shown as follows.

\begin{align}\begin{aligned}i_t & = \sigma(W_{x_i}x_{t} + W_{h_i}h_{t-1} + W_{c_i}c_{t-1} + b_i)\\f_t & = \sigma(W_{x_f}x_{t} + W_{h_f}h_{t-1} + W_{c_f}c_{t-1} + b_f)\\c_t & = f_tc_{t-1} + i_t tanh (W_{x_c}x_t+W_{h_c}h_{t-1} + b_c)\\o_t & = \sigma(W_{x_o}x_{t} + W_{h_o}h_{t-1} + W_{c_o}c_t + b_o)\\h_t & = o_t tanh(c_t)\end{aligned}\end{align}

The input of lstm step is $$Wx_t + Wh_{t-1}$$, and user should use mixed and full_matrix_projection to calculate these input vectors.

The state of lstm step is $$c_{t-1}$$. And lstm step layer will do

\begin{align}\begin{aligned}i_t = \sigma(input + W_{ci}c_{t-1} + b_i)\\...\end{aligned}\end{align}

This layer has two outputs. Default output is $$h_t$$. The other output is $$o_t$$, whose name is ‘state’ and can use get_output to extract this output.

参数: name (basestring) – The name of this layer. It is optional. size (int) – Layer’s size. NOTE: lstm layer’s size, should be equal to input.size/4, and should be equal to state.size. input (paddle.v2.config_base.Layer) – input layer. $$Wx_t + Wh_{t-1}$$ state (paddle.v2.config_base.Layer) – State Layer. $$c_{t-1}$$ act (paddle.v2.activation.Base) – Activation type. Default is tanh gate_act (paddle.v2.activation.Base) – Gate Activation Type. Default is sigmoid, and should be sigmoid only. state_act (paddle.v2.activation.Base) – State Activation Type. Default is sigmoid, and should be sigmoid only. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttribute) – layer’s extra attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### gru_step¶

class paddle.v2.layer.gru_step
参数: input (paddle.v2.config_base.Layer) – output_mem – size – act – name – The name of this layer. It is optional. gate_act – bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. param_attr – the parameter_attribute for transforming the output_mem from previous step. layer_attr – paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### get_output¶

class paddle.v2.layer.get_output

Get layer’s output by name. In PaddlePaddle, a layer might return multiple values, but returns one layer’s output. If the user wants to use another output besides the default one, please use get_output first to get the output from input.

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – get output layer’s input. And this layer should contains multiple outputs. arg_name (basestring) – Output name from input. layer_attr – Layer’s extra attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Mixed Layer¶

### mixed¶

class paddle.v2.layer.mixed

Mixed Layer. A mixed layer will add all inputs together, then activate. Each inputs is a projection or operator.

There are two styles of usages.

1. When not set inputs parameter, use mixed like this:
with mixed(size=256) as m:
m += full_matrix_projection(input=layer1)
m += identity_projection(input=layer2)

1. You can also set all inputs when invoke mixed as follows:
m = mixed(size=256,
input=[full_matrix_projection(input=layer1),
full_matrix_projection(input=layer2)])

参数: name (basestring) – mixed layer name. Can be referenced by other layer. size (int) – layer size. input – inputs layer. It is an optional parameter. If set, then this function will just return layer’s name. act (paddle.v2.activation.Base) – Activation Type. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttribute) – The extra layer config. Default is None. MixedLayerType object can add inputs or layer name. MixedLayerType

### embedding¶

class paddle.v2.layer.embedding

Define a embedding Layer.

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – The input layer for this embedding. NOTE: must be Index Data. size (int) – The embedding dimension. param_attr (paddle.v2.attr.ParameterAttribute|None) – The embedding parameter attribute. See paddle.v2.attr.ParameterAttribute for details. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra layer Config. Default is None. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### scaling_projection¶

class paddle.v2.layer.scaling_projection

scaling_projection multiplies the input with a scalar parameter and add to the output.

$out += w * in$

The example usage is:

proj = scaling_projection(input=layer)

参数: input (paddle.v2.config_base.Layer) – Input Layer. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter config, None if use default. A ScalingProjection object ScalingProjection

### dotmul_projection¶

class paddle.v2.layer.dotmul_projection

DotMulProjection with a layer as input. It performs element-wise multiplication with weight.

$out.row[i] += in.row[i] .* weight$

where $$.*$$ means element-wise multiplication.

The example usage is:

proj = dotmul_projection(input=layer)

参数: input (paddle.v2.config_base.Layer) – Input layer. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter config, None if use default. A DotMulProjection Object. DotMulProjection

### dotmul_operator¶

class paddle.v2.layer.dotmul_operator

DotMulOperator takes two inputs and performs element-wise multiplication:

$out.row[i] += scale * (a.row[i] .* b.row[i])$

where $$.*$$ means element-wise multiplication, and scale is a config scalar, its default value is one.

The example usage is:

op = dotmul_operator(a=layer1, b=layer2, scale=0.5)

参数: a (paddle.v2.config_base.Layer) – Input layer1 b (paddle.v2.config_base.Layer) – Input layer2 scale (float) – config scalar, default value is one. A DotMulOperator Object. DotMulOperator

### full_matrix_projection¶

class paddle.v2.layer.full_matrix_projection

Full Matrix Projection. It performs full matrix multiplication.

$out.row[i] += in.row[i] * weight$

There are two styles of usage.

1. When used in mixed like this, you can only set the input:
with mixed(size=100) as m:
m += full_matrix_projection(input=layer)

1. When used as an independant object like this, you must set the size:
proj = full_matrix_projection(input=layer,
size=100,
param_attr=ParamAttr(name='_proj'))

参数: input (paddle.v2.config_base.Layer) – input layer size (int) – The parameter size. Means the width of parameter. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter config, None if use default. A FullMatrixProjection Object. FullMatrixProjection

### identity_projection¶

class paddle.v2.layer.identity_projection
1. IdentityProjection if offset=None. It performs:
$out.row[i] += in.row[i]$

The example usage is:

proj = identity_projection(input=layer)


2. IdentityOffsetProjection if offset!=None. It likes IdentityProjection, but layer size may be smaller than input size. It select dimesions [offset, offset+layer_size) from input:

$out.row[i] += in.row[i + \textrm{offset}]$

The example usage is:

proj = identity_projection(input=layer,
offset=10)


Note that both of two projections should not have any parameter.

参数: input (paddle.v2.config_base.Layer) – Input Layer. offset (int) – Offset, None if use default. A IdentityProjection or IdentityOffsetProjection object IdentityProjection or IdentityOffsetProjection

### slice_projection¶

class paddle.v2.layer.slice_projection

slice_projection can slice the input value into multiple parts, and then select some of them to merge into a new output.

$output = [input.slices()]$

The example usage is:

proj = slice_projection(input=layer, slices=[(0, 10), (20, 30)])


Note that slice_projection should not have any parameter.

参数: input (paddle.v2.config_base.Layer) – Input Layer. slices (pair of int) – An array of slice parameters. Each slice contains the start and end offsets based on the input. A SliceProjection object SliceProjection

### table_projection¶

class paddle.v2.layer.table_projection

Table Projection. It selects rows from parameter where row_id is in input_ids.

$out.row[i] += table.row[ids[i]]$

where $$out$$ is output, $$table$$ is parameter, $$ids$$ is input_ids, and $$i$$ is row_id.

There are two styles of usage.

1. When used in mixed like this, you can only set the input:
with mixed(size=100) as m:
m += table_projection(input=layer)

1. When used as an independant object like this, you must set the size:
proj = table_projection(input=layer,
size=100,
param_attr=ParamAttr(name='_proj'))

参数: input (paddle.v2.config_base.Layer) – Input layer, which must contains id fields. size (int) – The parameter size. Means the width of parameter. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter config, None if use default. A TableProjection Object. TableProjection

### trans_full_matrix_projection¶

class paddle.v2.layer.trans_full_matrix_projection

Different from full_matrix_projection, this projection performs matrix multiplication, using transpose of weight.

$out.row[i] += in.row[i] * w^\mathrm{T}$

$$w^\mathrm{T}$$ means transpose of weight. The simply usage is:

proj = trans_full_matrix_projection(input=layer,
size=100,
param_attr=ParamAttr(
name='_proj',
initial_mean=0.0,
initial_std=0.01))

参数: input (paddle.v2.config_base.Layer) – input layer size (int) – The parameter size. Means the width of parameter. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter config, None if use default. A TransposedFullMatrixProjection Object. TransposedFullMatrixProjection

## Aggregate Layers¶

### AggregateLevel¶

class paddle.v2.layer.AggregateLevel

• SequenceType.NO_SEQUENCE means the sample is not a sequence.
• SequenceType.SEQUENCE means the sample is a sequence.
• SequenceType.SUB_SEQUENCE means the sample is a nested sequence, each timestep of which is also a sequence.

Accordingly, AggregateLevel supports two modes:

• AggregateLevel.TO_NO_SEQUENCE means the aggregation acts on each timestep of a sequence, both SUB_SEQUENCE and SEQUENCE will be aggregated to NO_SEQUENCE.
• AggregateLevel.TO_SEQUENCE means the aggregation acts on each sequence of a nested sequence, SUB_SEQUENCE will be aggregated to SEQUENCE.

### pooling¶

class paddle.v2.layer.pooling

Pooling layer for sequence inputs, not used for Image.

If stride > 0, this layer slides a window whose size is determined by stride, and return the pooling value of the window as the output. Thus, a long sequence will be shorten.

The parameter stride specifies the intervals at which to apply the pooling operation. Note that for sequence with sub-sequence, the default value of stride is -1.

The example usage is:

seq_pool = pooling(input=layer,
pooling_type=AvgPooling(),
agg_level=AggregateLevel.TO_NO_SEQUENCE)

参数: agg_level (AggregateLevel) – AggregateLevel.TO_NO_SEQUENCE or AggregateLevel.TO_SEQUENCE name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – input layer name. pooling_type (BasePoolingType|None) – Type of pooling, MaxPooling(default), AvgPooling, SumPooling, SquareRootNPooling. stride (Int) – The step size between successive pooling regions. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttributeNone) – The Extra Attributes for layer, such as dropout. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### last_seq¶

class paddle.v2.layer.last_seq

Get Last Timestamp Activation of a sequence.

If stride > 0, this layer slides a window whose size is determined by stride, and return the last value of the window as the output. Thus, a long sequence will be shorten. Note that for sequence with sub-sequence, the default value of stride is -1.

The simple usage is:

seq = last_seq(input=layer)

参数: agg_level – Aggregated level name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – Input layer name. stride (Int) – The step size between successive pooling regions. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### first_seq¶

class paddle.v2.layer.first_seq

Get First Timestamp Activation of a sequence.

If stride > 0, this layer slides a window whose size is determined by stride, and return the first value of the window as the output. Thus, a long sequence will be shorten. Note that for sequence with sub-sequence, the default value of stride is -1.

The simple usage is:

seq = first_seq(input=layer)

参数: agg_level – aggregation level name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – Input layer name. stride (Int) – The step size between successive pooling regions. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### concat¶

class paddle.v2.layer.concat

Concat all input vector into one huge vector. Inputs can be list of paddle.v2.config_base.Layer or list of projection.

The example usage is:

concat = concat(input=[layer1, layer2])

参数: name (basestring) – The name of this layer. It is optional. input (list|tuple|collections.Sequence) – input layers or projections act (paddle.v2.activation.Base) – Activation type. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### seq_concat¶

class paddle.v2.layer.seq_concat

Concat sequence a with sequence b.

Inputs:
• a = [a1, a2, ..., am]
• b = [b1, b2, ..., bn]

Output: [a1, ..., am, b1, ..., bn]

Note that the above computation is for one sample. Multiple samples are processed in one batch.

The example usage is:

concat = seq_concat(a=layer1, b=layer2)

参数: name (basestring) – The name of this layer. It is optional. a (paddle.v2.config_base.Layer) – input sequence layer b (paddle.v2.config_base.Layer) – input sequence layer act (paddle.v2.activation.Base) – Activation type. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### seq_slice¶

class paddle.v2.layer.seq_slice

seq_slice will return one or several sub-sequences from the input sequence layer given start and end indices.

• If only start indices are given, and end indices are set to None, this layer slices the input sequence from the given start indices to its end.
• If only end indices are given, and start indices are set to None, this layer slices the input sequence from its beginning to the given end indices.
• If start and end indices are both given, they should have the same number of elements.

If start or end indices contains more than one elements, the input sequence will be sliced for multiple times.

seq_silce = seq_slice(input=input_seq,
starts=start_pos, ends=end_pos)

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – input for this layer, it should be a sequence. starts (paddle.v2.config_base.Layer|None) – start indices to slice the input sequence. ends (paddle.v2.config_base.Layer|None) – end indices to slice the input sequence. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### sub_nested_seq¶

class paddle.v2.layer.sub_nested_seq

The sub_nested_seq accepts two inputs: the first one is a nested sequence; the second one is a set of selceted indices in the nested sequence.

Then sub_nest_seq trims the first nested sequence input according to the selected indices to form a new output. This layer is useful in beam training.

The example usage is:

sub_nest_seq = sub_nested_seq(input=[data, selected_indices])

参数: input (paddle.v2.config_base.Layer) – A nested sequence. selected_indices – a set of sequence indices in the nested sequence. name (basestring) – The name of this layer. It is optional. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Reshaping Layers¶

### block_expand¶

class paddle.v2.layer.block_expand
Expand feature map to minibatch matrix.
• matrix width is: block_y * block_x * num_channels
• matirx height is: outputH * outputW
\begin{align}\begin{aligned}outputH = 1 + (2 * padding_y + imgSizeH - block_y + stride_y - 1) / stride_y\\outputW = 1 + (2 * padding_x + imgSizeW - block_x + stride_x - 1) / stride_x\end{aligned}\end{align}

The expand method is the same with ExpandConvLayer, but saved the transposed value. After expanding, output.sequenceStartPositions will store timeline. The number of time steps are outputH * outputW and the dimension of each time step is block_y * block_x * num_channels. This layer can be used after convolution neural network, and before recurrent neural network.

The simple usage is:

block_expand = block_expand(input=layer,
num_channels=128,
stride_x=1,
stride_y=1,
block_x=1,
block_x=3)

参数: input (paddle.v2.config_base.Layer) – The input layer. num_channels (int|None) – The channel number of input layer. block_x (int) – The width of sub block. block_y (int) – The width of sub block. stride_x (int) – The stride size in horizontal direction. stride_y (int) – The stride size in vertical direction. padding_x (int) – The padding size in horizontal direction. padding_y (int) – The padding size in vertical direction. name (None|basestring.) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### ExpandLevel¶

class paddle.v2.layer.ExpandLevel

ExpandLevel supports two modes:

• ExpandLevel.FROM_NO_SEQUENCE means the expansion acts on NO_SEQUENCE, which will be expanded to SEQUENCE or SUB_SEQUENCE.
• ExpandLevel.FROM_SEQUENCE means the expansion acts on SEQUENCE, which will be expanded to SUB_SEQUENCE.

### expand¶

class paddle.v2.layer.expand

A layer for “Expand Dense data or (sequence data where the length of each sequence is one) to sequence data.”

The example usage is:

expand = expand(input=layer1,
expand_as=layer2,
expand_level=ExpandLevel.FROM_NO_SEQUENCE)

参数: input (paddle.v2.config_base.Layer) – Input layer expand_as (paddle.v2.config_base.Layer) – Expand as this layer’s sequence info. name (basestring) – The name of this layer. It is optional. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. expand_level (ExpandLevel) – whether input layer is timestep(default) or sequence. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### repeat¶

class paddle.v2.layer.repeat

A layer for repeating the input for num_repeats times.

If as_row_vector: .. math:

y  = [x_1,\cdots, x_n, \cdots, x_1, \cdots, x_n]


If not as_row_vector: .. math:

y  = [x_1,\cdots, x_1, \cdots, x_n, \cdots, x_n]


The example usage is:

expand = repeat(input=layer, num_repeats=4)

参数: input (paddle.v2.config_base.Layer) – Input layer num_repeats (int) – Repeat the input so many times name (basestring) – The name of this layer. It is optional. as_row_vector (bool) – True for treating input as row vector and repeating in the column direction. This is equivalent to apply concat() with num_repeats same input. False for treating input as column vector and repeating in the row direction. act (paddle.v2.activation.Base) – Activation type. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### rotate¶

class paddle.v2.layer.rotate

A layer for rotating 90 degrees (clock-wise) for each feature channel, usually used when the input sample is some image or feature map.

$y(j,i,:) = x(M-i-1,j,:)$

where $$x$$ is (M x N x C) input, and $$y$$ is (N x M x C) output.

The example usage is:

rot = rotate(input=layer,
height=100,
width=100)

参数: input (paddle.v2.config_base.Layer) – Input layer. height (int) – The height of the sample matrix name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### seq_reshape¶

class paddle.v2.layer.seq_reshape

A layer for reshaping the sequence. Assume the input sequence has T instances, the dimension of each instance is M, and the input reshape_size is N, then the output sequence has T*M/N instances, the dimension of each instance is N.

Note that T*M/N must be an integer.

The example usage is:

reshape = seq_reshape(input=layer, reshape_size=4)

参数: input (paddle.v2.config_base.Layer) – Input layer. reshape_size (int) – the size of reshaped sequence. name (basestring) – The name of this layer. It is optional. act (paddle.v2.activation.Base) – Activation type. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Math Layers¶

class paddle.v2.layer.addto

$y = f(\sum_{i} x_i + b)$

where $$y$$ is output, $$x$$ is input, $$b$$ is bias, and $$f$$ is activation function.

The example usage is:

addto = addto(input=[layer1, layer2],
bias_attr=False)


This layer just simply add all input layers together, then activate the sum inputs. Each input of this layer should be the same size, which is also the output size of this layer.

There is no weight matrix for each input, because it just a simple add operation. If you want a complicated operation before add, please use mixed.

It is a very good way to set dropout outside the layers. Since not all PaddlePaddle layer support dropout, you can add an add_to layer, set dropout here. Please refer to dropout for details.

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer|list|tuple) – Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of paddle.v2.config_base.Layer. act (paddle.v2.activation.Base) – Activation Type, default is tanh. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### linear_comb¶

class paddle.v2.layer.linear_comb
A layer for weighted sum of vectors takes two inputs.
• Input: size of weights is M
size of vectors is M*N
• Output: a vector of size=N
$z(i) = \sum_{j=0}^{M-1} x(j) y(i+Nj)$

where $$0 \le i \le N-1$$

Or in the matrix notation:

$z = x^\mathrm{T} Y$
In this formular:
• $$x$$: weights
• $$y$$: vectors.
• $$z$$: the output.

Note that the above computation is for one sample. Multiple samples are processed in one batch.

The simple usage is:

linear_comb = linear_comb(weights=weight, vectors=vectors,
size=elem_dim)

参数: weights (paddle.v2.config_base.Layer) – The weight layer. vectors (paddle.v2.config_base.Layer) – The vector layer. size (int) – the dimension of this layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### interpolation¶

class paddle.v2.layer.interpolation

This layer is for linear interpolation with two inputs, which is used in NEURAL TURING MACHINE.

$y.row[i] = w[i] * x_1.row[i] + (1 - w[i]) * x_2.row[i]$

where $$x_1$$ and $$x_2$$ are two (batchSize x dataDim) inputs, $$w$$ is (batchSize x 1) weight vector, and $$y$$ is (batchSize x dataDim) output.

The example usage is:

interpolation = interpolation(input=[layer1, layer2], weight=layer3)

参数: input (list|tuple) – Input layer. weight (paddle.v2.config_base.Layer) – Weight layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### bilinear_interp¶

class paddle.v2.layer.bilinear_interp

This layer is to implement bilinear interpolation on conv layer output.

The simple usage is:

bilinear = bilinear_interp(input=layer1, out_size_x=64, out_size_y=64)

参数: input (paddle.v2.config_base.Layer.) – A input layer. out_size_x (int|None) – bilinear interpolation output width. out_size_y (int|None) – bilinear interpolation output height. name (None|basestring) – The layer’s name, which cna not be specified. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### power¶

class paddle.v2.layer.power

This layer applies a power function to a vector element-wise, which is used in NEURAL TURING MACHINE.

$y = x^w$

where $$x$$ is a input vector, $$w$$ is scalar weight, and $$y$$ is a output vector.

The example usage is:

power = power(input=layer1, weight=layer2)

参数: input (paddle.v2.config_base.Layer) – Input layer. weight (paddle.v2.config_base.Layer) – Weight layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### scaling¶

class paddle.v2.layer.scaling

A layer for multiplying input vector by weight scalar.

$y = w x$

where $$x$$ is size=dataDim input, $$w$$ is size=1 weight, and $$y$$ is size=dataDim output.

Note that the above computation is for one sample. Multiple samples are processed in one batch.

The example usage is:

scale = scaling(input=layer1, weight=layer2)

参数: input (paddle.v2.config_base.Layer) – Input layer. weight (paddle.v2.config_base.Layer) – Weight layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### clip¶

class paddle.v2.layer.clip

A layer for clipping the input value by the threshold.

$out[i] = \min\left(\max\left(in[i],p_{1}$

ight),p_{2} ight)

clip = clip(input=input, min=-10, max=10)

param name: The name of this layer. It is optional. basestring The input layer. paddle.v2.config_base.Layer. The lower threshold for clipping. double The upper threshold for clipping. double paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### slope_intercept¶

class paddle.v2.layer.slope_intercept

This layer for applying a slope and an intercept to the input element-wise. There is no activation and weight.

$y = slope * x + intercept$

The simple usage is:

scale = slope_intercept(input=input, slope=-1.0, intercept=1.0)

参数: input (paddle.v2.config_base.Layer) – The input layer. name (basestring) – The name of this layer. It is optional. slope (float.) – the scale factor. intercept (float.) – the offset. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### tensor¶

class paddle.v2.layer.tensor

This layer performs tensor operation for two input. For example, each sample:

$y_{i} = a * W_{i} * {b^\mathrm{T}}, i=0,1,...,K-1$
In this formular:
• $$a$$: the first input contains M elements.
• $$b$$: the second input contains N elements.
• $$y_{i}$$: the i-th element of y.
• $$W_{i}$$: the i-th learned weight, shape if [M, N]
• $$b^\mathrm{T}$$: the transpose of $$b_{2}$$.

The simple usage is:

tensor = tensor(a=layer1, b=layer2, size=1000)

参数: name (basestring) – The name of this layer. It is optional. a (paddle.v2.config_base.Layer) – Input layer a. b (paddle.v2.config_base.Layer) – input layer b. size (int.) – the layer dimension. act (paddle.v2.activation.Base) – Activation Type. Default is tanh. param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### cos_sim¶

class paddle.v2.layer.cos_sim

Cosine Similarity Layer. The cosine similarity equation is here.

$similarity = cos(\theta) = {\mathbf{a} \cdot \mathbf{b} \over \|\mathbf{a}\| \|\mathbf{b}\|}$

The size of a is M, size of b is M*N, Similarity will be calculated N times by step M. The output size is N. The scale will be multiplied to similarity.

Note that the above computation is for one sample. Multiple samples are processed in one batch.

The example usage is:

cos = cos_sim(a=layer1, b=layer2, size=3)

参数: name (basestring) – The name of this layer. It is optional. a (paddle.v2.config_base.Layer) – input layer a b (paddle.v2.config_base.Layer) – input layer b scale (float) – scale for cosine value. default is 5. size (int) – layer size. NOTE size_a * size should equal size_b. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### trans¶

class paddle.v2.layer.trans

A layer for transposing a minibatch matrix.

$y = x^\mathrm{T}$

where $$x$$ is (M x N) input, and $$y$$ is (N x M) output.

The example usage is:

trans = trans(input=layer)

参数: input (paddle.v2.config_base.Layer) – Input layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### scale_shift¶

class paddle.v2.layer.scale_shift

A layer applies a linear transformation to each element in each row of the input matrix. For each element, the layer first re-scale it and then adds a bias to it.

This layer is very like the SlopeInterceptLayer, except the scale and bias are trainable.

$y = w * x + b$
scale_shift = scale_shift(input=input, bias_attr=False)

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer.) – The input layer. param_attr (paddle.v2.attr.ParameterAttribute) – The parameter attribute of scaling. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Sampling Layers¶

### maxid¶

class paddle.v2.layer.max_id

A layer for finding the id which has the maximal value for each sample. The result is stored in output.ids.

The example usage is:

maxid = maxid(input=layer)

参数: input (paddle.v2.config_base.Layer) – Input layer name. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### sampling_id¶

class paddle.v2.layer.sampling_id

A layer for sampling id from multinomial distribution from the input layer. Sampling one id for one sample.

The simple usage is:

samping_id = sampling_id(input=input)

参数: input (paddle.v2.config_base.Layer) – The input layer. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### multiplex¶

class paddle.v2.layer.multiplex

This layer multiplex multiple layers according to the index, which is provided by the first input layer. inputs[0]: the index of the layer to output of size batchSize. inputs[1:N]; the candidate output data. For each index i from 0 to batchSize -1, the output is the i-th row of the (index[i] + 1)-th layer.

For each i-th row of output: .. math:

y[i][j] = x_{x_{0}[i] + 1}[i][j], j = 0,1, ... , (x_{1}.width - 1)


where, y is output. $$x_{k}$$ is the k-th input layer and $$k = x_{0}[i] + 1$$.

The example usage is:

maxid = multiplex(input=layers)

参数: input (list of paddle.v2.config_base.Layer) – Input layers. name (basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Slicing and Joining Layers¶

class paddle.v2.layer.pad

For example, pad_c=[2,3] means padding 2 zeros before the input data and 3 zeros after the input data in channel dimension. pad_h means padding zeros in height dimension. pad_w means padding zeros in width dimension.

For example,

input(2,2,2,3)  = [
[ [[1,2,3], [3,4,5]],
[[2,3,5], [1,6,7]] ],
[ [[4,3,1], [1,8,7]],
[[3,8,9], [2,3,5]] ]
]

output(2,4,2,3) = [
[ [[0,0,0], [0,0,0]],
[[1,2,3], [3,4,5]],
[[2,3,5], [1,6,7]],
[[0,0,0], [0,0,0]] ],
[ [[0,0,0], [0,0,0]],
[[4,3,1], [1,8,7]],
[[3,8,9], [2,3,5]],
[[0,0,0], [0,0,0]] ]
]


The simply usage is:

pad = pad(input=ipt,


## Cost Layers¶

### cross_entropy_cost¶

class paddle.v2.layer.cross_entropy_cost

A loss layer for multi class entropy.

The example usage is:

cost = cross_entropy(input=input,
label=label)

参数: input (paddle.v2.config_base.Layer.) – The first input layer. label – The input label. name (None|basestring.) – The name of this layer. It is optional. coeff (float.) – The cost is multiplied with coeff. The coefficient affects the gradient in the backward. weight (LayerOutout) – The cost of each sample is multiplied with each weight. The weight should be a layer with size=1. Note that gradient will not be calculated for weight. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer.

### cross_entropy_with_selfnorm_cost¶

class paddle.v2.layer.cross_entropy_with_selfnorm_cost

A loss layer for multi class entropy with selfnorm. Input should be a vector of positive numbers, without normalization.

The example usage is:

cost = cross_entropy_with_selfnorm(input=input,
label=label)

参数: input (paddle.v2.config_base.Layer.) – The first input layer. label – The input label. name (None|basestring.) – The name of this layer. It is optional. coeff (float.) – The coefficient affects the gradient in the backward. softmax_selfnorm_alpha (float.) – The scale factor affects the cost. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer.

### multi_binary_label_cross_entropy_cost¶

class paddle.v2.layer.multi_binary_label_cross_entropy_cost

A loss layer for multi binary label cross entropy.

The example usage is:

cost = multi_binary_label_cross_entropy(input=input,
label=label)

参数: input (paddle.v2.config_base.Layer) – The first input layer. label – The input label. name (None|basestring) – The name of this layer. It is optional. coeff (float) – The coefficient affects the gradient in the backward. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### huber_regression_cost¶

class paddle.v2.layer.huber_regression_cost
In statistics, the Huber loss is a loss function used in robust regression, that is less sensitive to outliers in data than the squared error loss. Given a prediction f(x), a label y and $$\delta$$, the loss function is defined as:

ight )^2, left | y-f(x) ight |leq delta

loss = delta left | y-f(x)

ight |-0.5delta ^2, otherwise

The example usage is:

cost = huber_regression_cost(input=input, label=label)

param input: type input: The first input layer. paddle.v2.config_base.Layer. The input label. paddle.v2.config_base.Layer. The name of this layer. It is optional. None|basestring. The difference between the observed and predicted values. float. The coefficient affects the gradient in the backward. float. Extra Layer Attribute. paddle.v2.attr.ExtraAttribute paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer.

### huber_classification_cost¶

class paddle.v2.layer.huber_classification_cost
For classification purposes, a variant of the Huber loss called modified Huber is sometimes used. Given a prediction f(x) (a real-valued classifier score) and a true binary class label :math:yin left {-1, 1
ight }, the modified Huber
loss is defined as:
ight )^2, yf(x)geq 1
loss = -4yf(x), ext{otherwise}

The example usage is:

cost = huber_classification_cost(input=input, label=label)

param input: type input: The first input layer. paddle.v2.config_base.Layer. The input label. paddle.v2.config_base.Layer. The name of this layer. It is optional. None|basestring. The coefficient affects the gradient in the backward. float. Extra Layer Attribute. paddle.v2.attr.ExtraAttribute paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer.

### lambda_cost¶

class paddle.v2.layer.lambda_cost

lambdaCost for lambdaRank LTR approach.

The example usage is:

cost = lambda_cost(input=input,
score=score,
NDCG_num=8,
max_sort_size=-1)

参数: input (paddle.v2.config_base.Layer) – Samples of the same query should be loaded as sequence. score – The 2nd input. Score of each sample. NDCG_num (int) – The size of NDCG (Normalized Discounted Cumulative Gain), e.g., 5 for NDCG@5. It must be less than or equal to the minimum size of lists. max_sort_size (int) – The size of partial sorting in calculating gradient. If max_sort_size = -1, then for each list, the algorithm will sort the entire list to get gradient. In other cases, max_sort_size must be greater than or equal to NDCG_num. And if max_sort_size is greater than the size of a list, the algorithm will sort the entire list of get gradient. name (None|basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### square_error_cost¶

class paddle.v2.layer.square_error_cost

sum of square error cost:

$cost = \sum_{i=1}^N(t_i-y_i)^2$
参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – Network prediction. label (paddle.v2.config_base.Layer) – Data label. weight (paddle.v2.config_base.Layer) – The weight affects the cost, namely the scale of cost. It is an optional argument. coeff (float) – The coefficient affects the gradient in the backward. layer_attr (paddle.v2.attr.ExtraAttribute) – layer’s extra attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### rank_cost¶

class paddle.v2.layer.rank_cost

A cost Layer for learning to rank using gradient descent. Details can refer to papers. This layer contains at least three inputs. The weight is an optional argument, which affects the cost.

\begin{align}\begin{aligned}C_{i,j} & = -\tilde{P_{ij}} * o_{i,j} + log(1 + e^{o_{i,j}})\\o_{i,j} & = o_i - o_j\\\tilde{P_{i,j}} & = \{0, 0.5, 1\} \ or \ \{0, 1\}\end{aligned}\end{align}
In this formula:
• $$C_{i,j}$$ is the cross entropy cost.
• $$\tilde{P_{i,j}}$$ is the label. 1 means positive order and 0 means reverse order.
• $$o_i$$ and $$o_j$$: the left output and right output. Their dimension is one.

The example usage is:

cost = rank_cost(left=out_left,
right=out_right,
label=label)

参数: left (paddle.v2.config_base.Layer) – The first input, the size of this layer is 1. right (paddle.v2.config_base.Layer) – The right input, the size of this layer is 1. label (paddle.v2.config_base.Layer) – Label is 1 or 0, means positive order and reverse order. weight (paddle.v2.config_base.Layer) – The weight affects the cost, namely the scale of cost. It is an optional argument. name (None|basestring) – The name of this layer. It is optional. coeff (float) – The coefficient affects the gradient in the backward. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### sum_cost¶

class paddle.v2.layer.sum_cost

A loss layer which calculate the sum of the input as loss

The example usage is:

cost = sum_cost(input=input)

参数: input (paddle.v2.config_base.Layer.) – The first input layer. name (None|basestring.) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer.

### crf¶

class paddle.v2.layer.crf

A layer for calculating the cost of sequential conditional random field model.

The example usage is:

crf = crf(input=input,
label=label,
size=label_dim)

参数: input (paddle.v2.config_base.Layer) – The first input layer is the feature. label (paddle.v2.config_base.Layer) – The second input layer is label. size (int) – The category number. weight (paddle.v2.config_base.Layer) – The third layer is “weight” of each sample, which is an optional argument. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter attribute. None means default attribute name (None|basestring) – The name of this layer. It is optional. coeff (float) – The coefficient affects the gradient in the backward. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### crf_decoding¶

class paddle.v2.layer.crf_decoding

A layer for calculating the decoding sequence of sequential conditional random field model. The decoding sequence is stored in output.ids. If a second input is provided, it is treated as the ground-truth label, and this layer will also calculate error. output.value[i] is 1 for incorrect decoding or 0 for correct decoding.

The example usage is:

crf_decoding = crf_decoding(input=input,
size=label_dim)

参数: input (paddle.v2.config_base.Layer) – The first input layer. size (int) – size of this layer. label (paddle.v2.config_base.Layer or None) – None or ground-truth label. param_attr (paddle.v2.attr.ParameterAttribute) – Parameter attribute. None means default attribute name (None|basestring) – The name of this layer. It is optional. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### ctc¶

class paddle.v2.layer.ctc

Connectionist Temporal Classification (CTC) is designed for temporal classication task. That is, for sequence labeling problems where the alignment between the inputs and the target labels is unknown.

More details can be found by referring to Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks

Considering the ‘blank’ label needed by CTC, you need to use (num_classes + 1) as the input size. num_classes is the category number. And the ‘blank’ is the last category index. So the size of ‘input’ layer, such as fc with softmax activation, should be num_classes + 1. The size of ctc should also be num_classes + 1.

The example usage is:

ctc = ctc(input=input,
label=label,
size=9055,
norm_by_times=True)

参数: input (paddle.v2.config_base.Layer) – The input layer. label (paddle.v2.config_base.Layer) – The data layer of label with variable length. size (int) – category numbers + 1. name (basestring|None) – The name of this layer. It is optional. norm_by_times (bool) – Whether to normalization by times. False by default. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### warp_ctc¶

class paddle.v2.layer.warp_ctc

A layer intergrating the open-source warp-ctc library, which is used in Deep Speech 2: End-toEnd Speech Recognition in English and Mandarin, to compute Connectionist Temporal Classification (CTC) loss. Besides, another warp-ctc repository, which is forked from the official one, is maintained to enable more compiling options. During the building process, PaddlePaddle will clone the source codes, build and install it to third_party/install/warpctc directory.

More details of CTC can be found by referring to Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks.

• Let num_classes represent the category number. Considering the ‘blank’ label needed by CTC, you need to use (num_classes + 1) as the input size. Thus, the size of both warp_ctc layer and ‘input’ layer should be set to num_classes + 1.
• You can set ‘blank’ to any value ranged in [0, num_classes], which should be consistent as that used in your labels.
• As a native ‘softmax’ activation is interated to the warp-ctc library, ‘linear’ activation is expected instead in the ‘input’ layer.

The example usage is:

ctc = warp_ctc(input=input,
label=label,
size=1001,
blank=1000,
norm_by_times=False)

参数: input (paddle.v2.config_base.Layer) – The input layer. label (paddle.v2.config_base.Layer) – The data layer of label with variable length. size (int) – category numbers + 1. name (basestring|None) – The name of this layer. It is optional. blank (int) – the ‘blank’ label used in ctc norm_by_times (bool) – Whether to normalization by times. False by default. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra Layer config. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### nce¶

class paddle.v2.layer.nce

Noise-contrastive estimation. Implements the method in the following paper: A fast and simple algorithm for training neural probabilistic language models.

The example usage is:

cost = nce(input=[layer1, layer2], label=layer2,
param_attr=[attr1, attr2], weight=layer3,
num_classes=3, neg_distribution=[0.1,0.3,0.6])


### hsigmoid¶

class paddle.v2.layer.hsigmoid

Organize the classes into a binary tree. At each node, a sigmoid function is used to calculate the probability of belonging to the right branch. This idea is from “F. Morin, Y. Bengio (AISTATS 05): Hierarchical Probabilistic Neural Network Language Model.”

The example usage is:

cost = hsigmoid(input=[layer1, layer2],
label=data)

参数: input (paddle.v2.config_base.Layer|list|tuple) – Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of paddle.v2.config_base.Layer. label (paddle.v2.config_base.Layer) – Label layer. num_classes (int|None) – number of classes. name (basestring) – The name of this layer. It is optional. bias_attr (paddle.v2.attr.ParameterAttribute|None|Bool|Any) – The Bias Attribute. If the parameter is set to False or something not type of paddle.v2.attr.ParameterAttribute, no bias is defined. If the parameter is set to True, the bias is initialized to zero. param_attr (paddle.v2.attr.ParameterAttribute|None) – Parameter Attribute. None means default parameter. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### smooth_l1_cost¶

class paddle.v2.layer.smooth_l1_cost

This is a L1 loss but more smooth. It requires that the size of input and label are equal. The formula is as follows,

$L = \sum_{i} smooth_{L1}(input_i - label_i)$

in which

$\begin{split}smooth_{L1}(x) = \begin{cases} 0.5x^2& \text{if} \ |x| < 1 \\ |x|-0.5& \text{otherwise} \end{cases}\end{split}$

More details can be found by referring to Fast R-CNN

The example usage is:

cost = smooth_l1_cost(input=input,
label=label)

参数: input (paddle.v2.config_base.Layer) – The input layer. label – The input label. name (None|basestring) – The name of this layer. It is optional. coeff (float) – The coefficient affects the gradient in the backward. layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### multibox_loss¶

class paddle.v2.layer.multibox_loss

Compute the location loss and the confidence loss for ssd.

参数: name (basestring) – The name of this layer. It is optional. input_loc (paddle.v2.config_base.Layer | List of paddle.v2.config_base.Layer) – The input predict locations. input_conf (paddle.v2.config_base.Layer | List of paddle.v2.config_base.Layer) – The input priorbox confidence. priorbox (paddle.v2.config_base.Layer) – The input priorbox location and the variance. label (paddle.v2.config_base.Layer) – The input label. num_classes (int) – The number of the classification. overlap_threshold (float) – The threshold of the overlap. neg_pos_ratio (float) – The ratio of the negative bbox to the positive bbox. neg_overlap (float) – The negative bbox overlap threshold. background_id (int) – The background class index. paddle.v2.config_base.Layer

## Check Layer¶

### eos¶

class paddle.v2.layer.eos

A layer for checking EOS for each sample: - output_id = (input_id == conf.eos_id)

The result is stored in output_.ids. It is used by recurrent layer group.

The example usage is:

eos = eos(input=layer, eos_id=id)

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – Input layer name. eos_id (int) – end id of sequence layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Miscs¶

### dropout¶

class paddle.v2.layer.dropout

The example usage is:

dropout = dropout(input=input, dropout_rate=0.5)

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – The input layer. dropout_rate (float) – The probability of dropout. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

## Activation with learnable parameter¶

### prelu¶

class paddle.v2.layer.prelu

The Parameter Relu activation that actives outputs with a learnable weight.

Reference:
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification http://arxiv.org/pdf/1502.01852v1.pdf
$\begin{split}z_i &\quad if \quad z_i > 0 \\ a_i * z_i &\quad \mathrm{otherwise}\end{split}$

The example usage is:

prelu = prelu(input=layers, partial_sum=1)

参数: name (basestring) – The name of this layer. It is optional. input (paddle.v2.config_base.Layer) – The input layer. partial_sum (int) – this parameter makes a group of inputs share a same weight. partial_sum = 1, indicates the element-wise activation: each element has a weight. partial_sum = number of elements in one channel, indicates the channel-wise activation, elements in a channel share a same weight. partial_sum = number of outputs, indicates all elements share a same weight. param_attr (paddle.v2.attr.ParameterAttribute|None) – The parameter attribute. See paddle.v2.attr.ParameterAttribute for details. layer_attr (paddle.v2.attr.ExtraAttributeNone) – Extra layer configurations. Default is None. paddle.v2.config_base.Layer object. paddle.v2.config_base.Layer

### gated_unit¶

class paddle.v2.layer.gated_unit

The gated unit layer implements a simple gating mechanism over the input. The input $$X$$ is first projected into a new space $$X'$$, and it is also used to produce a gate weight $$\sigma$$. Element-wise product between :match:X’ and $$\sigma$$ is finally returned.

Reference:
Language Modeling with Gated Convolutional Networks https://arxiv.org/abs/1612.08083
$y=\text{act}(X \cdot W + b)\otimes \sigma(X \cdot V + c)$

The example usage is:

class paddle.v2.layer.detection_output`