《动手学深度学习：机器翻译及其相关技术；注意力机制与Seq2Seq模型；Transformer》
机器翻译
机器翻译（MT）：将一段文本从一种语言自动翻译为另一种语言，用神经网络解决这个问题通常称为神经机器翻译（NMT）。 主要特征：输出是单词序列而不是单个单词。 输出序列的长度可能与源序列的长度不同。
训练
def train_ch7(model, data_iter, lr, num_epochs, device): # Saved in d2l
model.to(device)
optimizer = optim.Adam(model.parameters(), lr=lr)
loss = MaskedSoftmaxCELoss()
tic = time.time()
for epoch in range(1, num_epochs+1):
l_sum, num_tokens_sum = 0.0, 0.0
for batch in data_iter:
optimizer.zero_grad()
X, X_vlen, Y, Y_vlen = [x.to(device) for x in batch]
Y_input, Y_label, Y_vlen = Y[:,:-1], Y[:,1:], Y_vlen-1
Y_hat, _ = model(X, Y_input, X_vlen, Y_vlen)
l = loss(Y_hat, Y_label, Y_vlen).sum()
l.backward()
with torch.no_grad():
d2l.grad_clipping_nn(model, 5, device)
num_tokens = Y_vlen.sum().item()
optimizer.step()
l_sum += l.sum().item()
num_tokens_sum += num_tokens
if epoch % 50 == 0:
print("epoch {0:4d},loss {1:.3f}, time {2:.1f} sec".format(
epoch, (l_sum/num_tokens_sum), time.time()-tic))
tic = time.time()
作者：zxj_45373271
相关文章
Iris
2021-08-03
Coral
2021-01-26
Belle
2020-06-06
Floria
2021-01-03
Ula
2023-05-13
Jacinda
2023-05-13
Winona
2023-05-13
Fawn
2023-05-13
Echo
2023-05-13
Maha
2023-05-13
Kande
2023-05-15
Viridis
2023-05-17
Pandora
2023-07-07
Tallulah
2023-07-17
Janna
2023-07-20
Ophelia
2023-07-20
Natalia
2023-07-20