model_architectures.py

import torch
import torch.nn as nn
from torch import optim
import torch.nn.functional as F

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

class Encoder_RNN(nn.Module):
    def __init__(self, input_size, hidden_size):
        super(Encoder_RNN, self).__init__()
        self.hidden_size = hidden_size
        self.embedding = nn.Embedding(input_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size)

    def forward(self, input, hidden):
        embed = self.embedding(input).view(1, 1, -1)
        output, hidden = self.gru(embed, hidden)
        # output and hidden are the same vectors
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)
    

class Decoder_RNN(nn.Module):
    def __init__(self, output_size, hidden_size):
        super(Decoder_RNN, self).__init__()
        self.hidden_size = hidden_size

        self.embedding = nn.Embedding(output_size, hidden_size)
        self.gru = nn.GRU(hidden_size, hidden_size)
        self.out = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax(dim=1)

    def forward(self, input, hidden):
        embed = self.embedding(input).view(1, 1, -1)
        embed = F.relu(embed)
        output, hidden = self.gru(embed, hidden)
        output = self.softmax(self.out(output[0]))
        return output, hidden

    def initHidden(self):
        return torch.zeros(1, 1, self.hidden_size, device=device)