transformer_generator.py

import math
import torch
from torch import nn, Tensor
from torch.nn import TransformerEncoder, TransformerEncoderLayer
from config import *
import math

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_seq_length, dropout=0.1):
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(p=dropout)
        
        pe = torch.zeros(max_seq_length, d_model)
        position = torch.arange(0, max_seq_length, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * -(math.log(10000.0) / d_model))
        
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        
        self.register_buffer('pe', pe.unsqueeze(0))
        
    def forward(self, x):
        x = x + self.pe[:, :x.size(1)]
        return self.dropout(x)
    

class TransformerModel(nn.Module):

    def __init__(self, max_seq_length: int, ntoken: int, d_model: int, nhead: int, d_hid: int,
                 nlayers: int, dropout: float = 0.5):
        super().__init__()
        self.model_type = 'Transformer'
        self.pos_encoder = PositionalEncoding(d_model, max_seq_length, dropout)
        encoder_layers = TransformerEncoderLayer(d_model, nhead, d_hid, dropout)
        self.transformer_encoder = TransformerEncoder(encoder_layers, nlayers)
        self.embedding = nn.Embedding(ntoken, d_model)
        self.d_model = d_model
        self.linear = nn.Linear(d_model, ntoken)

        self.init_weights()

    def init_weights(self) -> None:
        initrange = 0.1
        self.embedding.weight.data.uniform_(-initrange, initrange)
        self.linear.bias.data.zero_()
        self.linear.weight.data.uniform_(-initrange, initrange)

    def forward(self, src: Tensor, src_mask: Tensor = None) -> Tensor:
        src = self.embedding(src) * math.sqrt(self.d_model)
        src = self.pos_encoder(src)
        if src_mask is None:
            """Generate a square causal mask for the sequence. The masked positions are filled with float('-inf').
            Unmasked positions are filled with float(0.0).
            """
            src_mask = nn.Transformer.generate_square_subsequent_mask(len(src)).to(device)
            # Add padding mask if provided
        output = self.transformer_encoder(src, src_mask)
        output = self.linear(output)
        return output

model1 = TransformerModel(MAX_SEQ_LEN, VOCAB_SIZE, EMSIZE, NHEAD, D_HID, NLAYERS, dropout = 0.1).to(device)

class MultiHeadAttention(nn.Module):
    def __init__(self, d_model, num_heads):
        super(MultiHeadAttention, self).__init__()
        assert d_model % num_heads == 0, "d_model must be divisible by num_heads"
        
        self.d_model = d_model
        self.num_heads = num_heads
        self.d_k = d_model // num_heads
        
        self.W_q = nn.Linear(d_model, d_model)
        self.W_k = nn.Linear(d_model, d_model)
        self.W_v = nn.Linear(d_model, d_model)
        self.W_o = nn.Linear(d_model, d_model)
        
    def scaled_dot_product_attention(self, Q, K, V, mask=None):
        attn_scores = torch.matmul(Q, K.transpose(-2, -1)) / math.sqrt(self.d_k)
        if mask is not None:
            attn_scores = attn_scores.masked_fill(mask == 0, -1e9)
        attn_probs = torch.softmax(attn_scores, dim=-1)
        output = torch.matmul(attn_probs, V)
        return output
        
    def split_heads(self, x):
        batch_size, seq_length, d_model = x.size()
        return x.view(batch_size, seq_length, self.num_heads, self.d_k).transpose(1, 2)
        
    def combine_heads(self, x):
        batch_size, _, seq_length, d_k = x.size()
        return x.transpose(1, 2).contiguous().view(batch_size, seq_length, self.d_model)
        
    def forward(self, Q, K, V, mask=None):
        Q = self.split_heads(self.W_q(Q))
        K = self.split_heads(self.W_k(K))
        V = self.split_heads(self.W_v(V))
        
        attn_output = self.scaled_dot_product_attention(Q, K, V, mask)
        output = self.W_o(self.combine_heads(attn_output))
        return output

class PositionWiseFeedForward(nn.Module):
    def __init__(self, d_model, d_ff):
        super(PositionWiseFeedForward, self).__init__()
        self.fc1 = nn.Linear(d_model, d_ff)
        self.fc2 = nn.Linear(d_ff, d_model)
        self.relu = nn.ReLU()

    def forward(self, x):
        return self.fc2(self.relu(self.fc1(x)))

class PositionalEncoding1(nn.Module):
    def __init__(self, d_model, max_seq_length):
        super(PositionalEncoding1, self).__init__()
        
        pe = torch.zeros(max_seq_length, d_model)
        position = torch.arange(0, max_seq_length, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * -(math.log(10000.0) / d_model))
        
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        
        self.register_buffer('pe', pe.unsqueeze(0))
        
    def forward(self, x):
        return x + self.pe[:, :x.size(1)]

class EncoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout):
        super(EncoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = PositionWiseFeedForward(d_model, d_ff)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, mask):
        attn_output = self.self_attn(x, x, x, mask)
        x = self.norm1(x + self.dropout(attn_output))
        ff_output = self.feed_forward(x)
        x = self.norm2(x + self.dropout(ff_output))
        return x

class DecoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout):
        super(DecoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.cross_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = PositionWiseFeedForward(d_model, d_ff)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, enc_output, src_mask, tgt_mask):
        attn_output = self.self_attn(x, x, x, tgt_mask)
        x = self.norm1(x + self.dropout(attn_output))
        attn_output = self.cross_attn(x, enc_output, enc_output, src_mask)
        x = self.norm2(x + self.dropout(attn_output))
        ff_output = self.feed_forward(x)
        x = self.norm3(x + self.dropout(ff_output))
        return x

class Transformer(nn.Module):
    def __init__(self, src_vocab_size, tgt_vocab_size, d_model, num_heads, num_layers, d_ff, max_seq_length, dropout):
        super(Transformer, self).__init__()
        self.encoder_embedding = nn.Embedding(src_vocab_size, d_model)
        self.decoder_embedding = nn.Embedding(tgt_vocab_size, d_model)
        self.positional_encoding = PositionalEncoding1(d_model, max_seq_length)

        self.encoder_layers = nn.ModuleList([EncoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])
        self.decoder_layers = nn.ModuleList([DecoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])

        self.fc = nn.Linear(d_model, tgt_vocab_size)
        self.dropout = nn.Dropout(dropout)

    def generate_mask(self, src, tgt):
        src_mask = (src != 0).unsqueeze(1).unsqueeze(2)
        tgt_mask = (tgt != 0).unsqueeze(1).unsqueeze(3)
        seq_length = tgt.size(1)
        nopeak_mask = (1 - torch.triu(torch.ones(1, seq_length, seq_length), diagonal=1)).bool().to(device)
        tgt_mask = tgt_mask & nopeak_mask
        return src_mask, tgt_mask

    def forward(self, src, tgt):
        src_mask, tgt_mask = self.generate_mask(src, tgt)
        src_embedded = self.dropout(self.positional_encoding(self.encoder_embedding(src)))
        tgt_embedded = self.dropout(self.positional_encoding(self.decoder_embedding(tgt)))

        enc_output = src_embedded
        for enc_layer in self.encoder_layers:
            enc_output = enc_layer(enc_output, src_mask)

        dec_output = tgt_embedded
        for dec_layer in self.decoder_layers:
            dec_output = dec_layer(dec_output, enc_output, src_mask, tgt_mask)

        output = self.fc(dec_output)
        return output

model2 = Transformer(VOCAB_SIZE, VOCAB_SIZE, D_HID, NHEAD, NLAYERS, EMSIZE, MAX_SEQ_LEN, dropout=0.2).to(device)
# model2.load_state_dict(torch.load('checkpoints/transformer.pt'))

# build a generator
class Generator(nn.Module):
    def __init__(self, vocab_size, max_seq_len, emsize, d_hid, nhead, nlayers, dropout):
        super(Generator, self).__init__()
        # TransformerModel(max_seq_len, ntokens, emsize, nhead, d_hid, nlayers, dropout).to(device)
        self.transformer = TransformerModel(max_seq_len, vocab_size, emsize, nhead, d_hid, nlayers, dropout)
        # self.fc = nn.Linear(dim, vocab_size)
        
    def forward(self, src):
        output = self.transformer(src)
        return output
    
model3 = Generator(VOCAB_SIZE, MAX_SEQ_LEN, EMSIZE, D_HID, NHEAD, NLAYERS, dropout=0.2).to(device)
# model3.load_state_dict(torch.load('checkpoints/generator.pt'))