block_zoo.transformer package

Submodules

block_zoo.transformer.MLP module

class block_zoo.transformer.MLP.MLP(layer_conf)

Bases: torch.nn.modules.module.Module

MLP layer

Parameters:layer_conf (MLPConf) – configuration of a layer

forward(string, string_len)

process input

Parameters:

• string_len (string,) –
• string (e.g.) – [batch_size, seq_len, dim], string_len (Tensor): [batch_size]

Returns:

[batch_size, seq_len, output_dim], [batch_size]

Return type:

Tensor

gelu(x)

class block_zoo.transformer.MLP.MLPConf(**kwargs)

Bases: block_zoo.BaseLayer.BaseConf

Configuration of MLP layer

Parameters:dropout (float) – the dropout of MLP layer

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

block_zoo.transformer.MultiHeadAttention module

class block_zoo.transformer.MultiHeadAttention.MultiHeadAttention(layer_conf)

Bases: torch.nn.modules.module.Module

MultiHeadAttention Layer

Parameters:layer_conf (MultiHeadAttentionConf) – configuration of a layer

forward(string, string_len)

process input

Parameters:

• string_len (string,) –
• string (e.g.) – [batch_size, seq_len, dim], string_len (Tensor): [batch_size]

Returns:

[batch_size, seq_len, output_dim], [batch_size]

Return type:

Tensor

merge_heads(x)

split_heads(x, k=False)

class block_zoo.transformer.MultiHeadAttention.MultiHeadAttentionConf(**kwargs)

Bases: block_zoo.BaseLayer.BaseConf

Configuration of MultiHeadAttention Layer

Parameters:

• n_head (int) – the head number of attention
• scale (bool) – if need to scale
• attn_dropout (float) – the dropout of attention layer
• resid_dropout (float) – the dropout of last Linear

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