Class: Secryst::TransformerEncoderLayer
- Inherits:
-
Torch::NN::Module
- Object
- Torch::NN::Module
- Secryst::TransformerEncoderLayer
- Defined in:
- lib/secryst/transformer.rb
Instance Method Summary collapse
-
#forward(src, src_mask: nil, src_key_padding_mask: nil) ⇒ Object
Pass the input through the encoder layer.
-
#initialize(d_model, nhead, dim_feedforward: 2048, dropout: 0.1, activation: "relu") ⇒ TransformerEncoderLayer
constructor
TransformerEncoderLayer is made up of self-attn and feedforward network.
Constructor Details
#initialize(d_model, nhead, dim_feedforward: 2048, dropout: 0.1, activation: "relu") ⇒ TransformerEncoderLayer
TransformerEncoderLayer is made up of self-attn and feedforward network. This standard encoder layer is based on the paper “Attention Is All You Need”. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, pages 6000-6010. Users may modify or implement in a different way during application. Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of intermediate layer, relu or gelu (default=relu).
- Examples
-
>>> encoder_layer = TransformerEncoderLayer.new(512, 8) >>> src = Torch.rand(10, 32, 512) >>> out = encoder_layer.call(src)
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 |
# File 'lib/secryst/transformer.rb', line 185 def initialize(d_model, nhead, dim_feedforward:2048, dropout:0.1, activation:"relu") super() @self_attn = MultiheadAttention.new(d_model, nhead, dropout: dropout) # Implementation of Feedforward model @linear1 = Torch::NN::Linear.new(d_model, dim_feedforward) @dropout = Torch::NN::Dropout.new(p: dropout) @linear2 = Torch::NN::Linear.new(dim_feedforward, d_model) @norm1 = Torch::NN::LayerNorm.new(d_model) @norm2 = Torch::NN::LayerNorm.new(d_model) @dropout1 = Torch::NN::Dropout.new(p: dropout) @dropout2 = Torch::NN::Dropout.new(p: dropout) @activation = _get_activation_fn(activation) end |
Instance Method Details
#forward(src, src_mask: nil, src_key_padding_mask: nil) ⇒ Object
Pass the input through the encoder layer. Args:
src: the sequence to the encoder layer (required).
src_mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
208 209 210 211 212 213 214 215 216 217 |
# File 'lib/secryst/transformer.rb', line 208 def forward(src, src_mask: nil, src_key_padding_mask: nil) src2 = @self_attn.call(src, src, src, attn_mask: src_mask, key_padding_mask: src_key_padding_mask)[0] src = src + @dropout1.call(src2) src = @norm1.call(src) src2 = @linear2.call(@dropout.call(@activation.call(@linear1.call(src)))) src = src + @dropout2.call(src2) src = @norm2.call(src) return src end |