model.py

import torch
import torch.nn as nn
import numpy as np

class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_len=5000):
        super().__init__()
        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-np.log(10000.0) / d_model))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        pe = pe.unsqueeze(0)
        self.register_buffer('pe', pe)
    
    def forward(self, x):
        x = x + self.pe[:, :x.size(1)]
        return x

class TransformerSentiment(nn.Module):
    def __init__(self, vocab_size, d_model=64, nhead=4, num_layers=2, dim_feedforward=256, max_len=512): 
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, d_model)
        self.pos_encoder = PositionalEncoding(d_model, max_len)
        encoder_layer = nn.TransformerEncoderLayer(d_model=d_model, nhead=nhead, dim_feedforward=dim_feedforward, batch_first=True)
        self.transformer_encoder = nn.TransformerEncoder(encoder_layer, num_layers=num_layers)
        self.fc = nn.Linear(d_model, 1)
        self.sigmoid = nn.Sigmoid()
    
    def forward(self, src, src_mask=None):
        src = self.embedding(src) * np.sqrt(self.embedding.embedding_dim)
        src = self.pos_encoder(src)
        output = self.transformer_encoder(src, src_key_padding_mask=src_mask)
        output = output.mean(dim=1)
        output = self.fc(output)
        return self.sigmoid(output)