Models/Vector2MIDI.py

from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence
import torch.nn as nn
import numpy as np
import torch

class Vector2MIDI(nn.Module):
    def __init__(self, input_dim, hidden_dim, n_vocab, dropout=0.2):
        super().__init__()  # 부모 클래스 생성자 호출
        self.input_fc = nn.Linear(input_dim, hidden_dim) # 입력 차원에서 은닉 차원으로 변환

        self.lstm = nn.LSTM(hidden_dim, hidden_dim, num_layers=2, batch_first=True, dropout=dropout) # 과적합 방지 드롭아웃 LSTM

        self.fc_mid = nn.Linear(hidden_dim, 256)
        self.fc_out = nn.Linear(256, n_vocab)

    def forward(self, x, lengths):
        # x: [batch, seq_len, input_dim]
        x = self.input_fc(x)

        # Token 길이가 Midi마다 다르니까 PackedSequence 변환 후 LSTM 처리
        packed = pack_padded_sequence(x, lengths.cpu(), batch_first=True, enforce_sorted=False) # 패딩 변환
        LSTM_out, _ = self.lstm(packed) # LSTM 처리
        padded, _ = pad_packed_sequence(LSTM_out, batch_first=True) # 패딩 복원

        # 최종 출력
        x = self.fc_mid(padded)
        return self.fc_out(x)  # [B, T, vocab_size]