block_zoo.embedding package

Submodules

block_zoo.embedding.CNNCharEmbedding module

class block_zoo.embedding.CNNCharEmbedding.CNNCharEmbedding(layer_conf)

Bases: block_zoo.BaseLayer.BaseLayer

This layer implements the character embedding use CNN :param layer_conf: configuration of CNNCharEmbedding :type layer_conf: CNNCharEmbeddingConf

forward(string)

Step1: [batch_size, seq_len, char num in words] -> [batch_size, seq_len * char num in words] Step2: lookup embedding matrix -> [batch_size, seq_len * char num in words, embedding_dim] reshape -> [batch_size * seq_len, char num in words, embedding_dim] Step3: after convolution operation, got [batch_size * seq_len, char num related, output_channel_num] Step4: max pooling on axis 1 and -reshape-> [batch_size * seq_len, output_channel_dim] Step5: reshape -> [batch_size, seq_len, output_channel_dim]

Parameters:string (Variable) – [[char ids of word1], [char ids of word2], […], …], shape: [batch_size, seq_len, char num in words] Returns:[batch_size, seq_len, output_dim] Return type:Variable

class block_zoo.embedding.CNNCharEmbedding.CNNCharEmbeddingConf(**kwargs)

Bases: block_zoo.BaseLayer.BaseConf

Configuration of CNNCharEmbedding

Parameters:

• dim (int, optional) – the dimension of character embedding after convolution. Default: 30
• embedding_matrix_dim (int, optional) – the dimension of character initialized embedding. Default: 30
• stride (int, optional) – Stride of the convolution. Default: 1
• padding (int, optional) – Zero-padding added to both sides of the input. Default: 0
• window_size (int, optional) – width of convolution kernel. Default: 3
• activation (Str, optional) – activation after convolution operation, can set null. Default: ‘ReLU’

declare()

Define things like “input_ranks” and “num_of_inputs”, which are certain with regard to your layer

num_of_input is N(N>0) means this layer accepts N inputs;

num_of_input is -1 means this layer accepts any number of inputs;

The rank here is not the same as matrix rank:

For a scalar, its rank is 0;

For a vector, its rank is 1;

For a matrix, its rank is 2;

For a cube of numbers, its rank is 3.

… For instance, the rank of (batch size, sequence length, hidden_dim) is 3.

if num_of_input > 0:

len(input_ranks) should be equal to num_of_input

elif num_of_input == -1:

input_ranks should be a list with only one element and the rank of all the inputs should be equal to that element.

NOTE: when we build the model, if num_of_input is -1, we would replace it with the real number of inputs and replace input_ranks with a list of real input_ranks.

Returns:None

default()

Define the default hyper parameters here. You can define these hyper parameters in your configuration file as well.

Returns:None

inference()

Inference things like output_dim, which may relies on defined hyper parameter such as hidden dim and input_dim

Returns:None

verify()

Define some necessary varification for your layer when we define the model.

If you define your own layer and rewrite this funciton, please add “super(YourLayerConf, self).verify()” at the beginning

Returns:None

Module contents