我正在创建一个模型来识别 RNN (LITMS) 中的项目名称
我获取数据,然后转换数据,然后创建 Baches,然后创建模型,然后创建训练函数正确但训练在这里停止(不工作):
这是我的代码
for e in range(epochs):
# initialize hidden state
h = net.init_hidden(batch_size)
for x, y in get_batches(data, batch_size, seq_length):
print ("the login the loob get_batches is succressfuly")
counter += 1
# One-hot encode our data and make them Torch tensors
x = one_hot_encode(x, n_chars)
inputs, targets = torch.from_numpy(x), torch.from_numpy(y)
if(train_on_gpu):
inputs, targets = inputs.cuda(), targets.cuda()
# Creating new variables for the hidden state, otherwise
# we'd backprop through the entire training history
h = tuple([each.data for each in h])
# zero accumulated gradients
net.zero_grad()
# get the output from the model
output, h = net(inputs, h)
# calculate the loss and perform backprop
loss = criterion(output, targets.view(batch_size*seq_length))
loss.backward()
# `clip_grad_norm` helps prevent the exploding gradient problem in RNNs / LSTMs.
nn.utils.clip_grad_norm_(net.parameters(), clip)
opt.step()
# loss stats
if counter % print_every == 0:
# Get validation loss
val_h = net.init_hidden(batch_size)
val_losses = []
net.eval()
for x, y in get_batches(val_data, batch_size, seq_length):
# One-hot encode our data and make them Torch tensors
x = one_hot_encode(x, n_chars)
x, y = torch.from_numpy(x), torch.from_numpy(y)
# Creating new variables for the hidden state, otherwise
# we'd backprop through the entire training history
val_h = tuple([each.data for each in val_h])
inputs, targets = x, y
if(train_on_gpu):
inputs, targets = inputs.cuda(), targets.cuda()
output, val_h = net(inputs, val_h)
val_loss = criterion(output, targets.view(batch_size*seq_length))
val_losses.append(val_loss.item())
net.train() # reset to train mode after iterationg through validation data
print("Epoch: {}/{}...".format(e+1, epochs),
"Step: {}...".format(counter),
"Loss: {:.4f}...".format(loss.item()),
"Val Loss: {:.4f}".format(np.mean(val_losses)))
我不知道为什么。
如果可以,请帮助我 您可以找到笔记本文件 here。