pythonlessons

random_decoder_input shape (1, 110)
decoder_embeddings shape (1, 110, 512)
decoder_output shape (1, 110, 512)

pythonlessons

random_encoder_input shape (1, 100)
encoder_output shape (1, 100, 512)

pythonlessons

encoder_embeddings shape (1, 100, 512)
encoder_layer_output shape (1, 100, 512)

pythonlessons

encoder_input_size = 100
decoder_input_size = 110

encoder_vocab_size = 1000
decoder_vocab_size = 1000

model = Transformer(
    input_vocab_size=encoder_vocab_size,
    target_vocab_size=decoder_vocab_size,
    encoder_input_size=encoder_input_size,

pythonlessons

def Transformer(
    input_vocab_size: int, 
    target_vocab_size: int, 
    encoder_input_size: int = None,
    decoder_input_size: int = None,
    num_layers: int=6, 
    d_model: int=512, 
    num_heads: int=8,
    dff: int=2048,
    dropout_rate: float=0.1,

pythonlessons

# Test decoder layer
decoder_vocab_size = 1000
d_model = 512

decoder_layer = Decoder(num_layers=2, d_model=d_model, num_heads=2, dff=2048, vocab_size=decoder_vocab_size)

random_decoder_input = np.random.randint(0, decoder_vocab_size, size=(1, 100))

decoder_output = decoder_layer(random_decoder_input, encoder_output)

pythonlessons

class Decoder(tf.keras.layers.Layer):
    """
    A custom TensorFlow layer that implements the Decoder. This layer is mostly used in the Transformer models
    for natural language processing tasks, such as machine translation, text summarization or text classification.

    Methods:
        call: Performs the forward pass of the layer.

    Attributes:
        d_model (int): The dimensionality of the model.

pythonlessons

# Test DecoderLayer layer
decoder_vocab_size = 1000
d_model = 512
dff = 2048
num_heads = 8

decoder_layer = DecoderLayer(d_model, num_heads, dff)

random_decoderLayer_input = np.random.randint(0, decoder_vocab_size, size=(1, 110))

pythonlessons

class DecoderLayer(tf.keras.layers.Layer):
    """
    A single layer of the Decoder. Usually there are multiple layers stacked on top of each other.
    
    Methods:
        call: Performs the forward pass of the layer.

    Attributes:
        causal_self_attention (CausalSelfAttention): The causal self-attention layer.
        cross_attention (CrossAttention): The cross-attention layer.

pythonlessons

encoder_vocab_size = 1000
d_model = 512

encoder = Encoder(num_layers=2, d_model=d_model, num_heads=2, dff=2048, vocab_size=encoder_vocab_size)

random_encoder_input = np.random.randint(0, encoder_vocab_size, size=(1, 100))

encoder_output = encoder(random_encoder_input)

print("random_encoder_input shape", random_encoder_input.shape)