Deep learning LSTM多对多同步序列输入和输出Pytorch损耗是否减少？
我正在一个项目中工作，我为seq2seq构建了一个LSTM模型，其中我有一个同步的序列输入和输出。我的音频时间序列长度为32000，我的标签长度也为32000。我们希望对每个音频样本进行分类（假音频或真音频）。我的张量是这样的，举个例子 时间序列Deep learning LSTM多对多同步序列输入和输出Pytorch损耗是否减少？,deep-learning,pytorch,lstm,recurrent-neural-network,seq2seq,Deep Learning,Pytorch,Lstm,Recurrent Neural Network,Seq2seq,我正在一个项目中工作，我为seq2seq构建了一个LSTM模型，其中我有一个同步的序列输入和输出。我的音频时间序列长度为32000，我的标签长度也为32000。我们希望对每个音频样本进行分类（假音频或真音频）。我的张量是这样的，举个例子 时间序列 tensor([-0.1635, -0.1510, -0.1455, ..., -0.3338, -0.3163, -0.2944]) 每个样本对应的标签0和1 tensor([0, 0, 0, ..., 0, 0, 0]) 在所有的音频中，大
tensor([-0.1635, -0.1510, -0.1455, ..., -0.3338, -0.3163, -0.2944])
tensor([0, 0, 0, ..., 0, 0, 0])
class LSTM(nn.Module):
def __init__(self, input_size, hidden_size, num_layers, output_dim = 2, batch_size = batch_size):
super(LSTM , self).__init__()
self.num_layers = num_layers
self.input_size = input_size
self.hidden_size = hidden_size
self.batch_size = batch_size
self.rnn_state = None
self.lstm = nn.LSTM(self.input_size , self.hidden_size , self.num_layers, batch_first = True)
self.to_linear = nn.Linear(self.hidden_size, output_dim)
def repackage_rnn_state(self):
self.rnn_state = self._detach_rnn_state(self.rnn_state)
def _detach_rnn_state(self, h):
if isinstance(h, torch.Tensor):
return h.detach()
else:
return tuple(self._detach_rnn_state(v) for v in h)
def forward(self, x):
lstm_out, self.rnn_state = self.lstm(x , self.rnn_state)
logits = self.to_linear(lstm_out)
scores = F.softmax(logits, dim = 2)
return scores
for epoch in range(num_epochs):
running_loss_train , accuracy_train = 0 , 0
network.hidden = network.init_hidden()
for batch_idx, batch in enumerate(train_loader):
new_time_series , new_labels = batch
new_time_series, new_labels = new_time_series.to(device), new_labels.to(device)
optimizer.zero_grad()
# forward pass feeding the padded sequence
preds = network(new_time_series.unsqueeze(2))
preds = preds.view(preds.shape[0]*preds.shape[1], preds.shape[2])
train_loss = criterion(preds, new_labels.flatten().long())
train_loss.backward()
# gradient clipping here just before the parameter updates, clips inplace, clip value = 1
torch.nn.utils.clip_grad_norm_(network.parameters(),clip)
optimizer.step()
running_loss_train+=train_loss.detach().item()/new_time_series.shape[0]
_ ,predictions = torch.max(preds,1)
metrics = get_evaluations_ignoring_padding(new_labels, predictions, 2)
accuracy_train+=metrics['Accuracy']
if batch_idx%100==0:
print('Epoch : %d | BatchID : %d | Train Loss : %.3f | Train Acc : %.3f ' %
(epoch , batch_idx, train_loss.item() / new_time_series.shape[0] ,
metrics['Accuracy']))