def train(input_variable, lengths, target_variable, mask, max_target_len, encoder, decoder, embedding,
encoder_optimizer, decoder_optimizer, batch_size, clip, max_length=MAX_LENGTH):
# Zero gradients
encoder_optimizer.zero_grad()
decoder_optimizer.zero_grad()
# Set device options
input_variable = input_variable.to(device)
lengths = lengths.to(device)
target_variable = target_variable.to(device)
mask = mask.to(device)
# Initialize variables
loss = 0
print_losses = []
n_totals = 0
# Forward pass through encoder
encoder_outputs, encoder_hidden = encoder(input_variable, lengths)
# Create initial decoder input (start with SOS tokens for each sentence)
decoder_input = torch.LongTensor([[SOS_token for _ in range(batch_size)]])
decoder_input = decoder_input.to(device)
# Set initial decoder hidden state to the encoder's final hidden state
decoder_hidden = encoder_hidden[:decoder.n_layers]
# Determine if we are using teacher forcing this iteration
use_teacher_forcing = True if random.random() < teacher_forcing_ratio else False
# Forward batch of sequences through decoder one time step at a time
if use_teacher_forcing:
for t in range(max_target_len):
decoder_output, decoder_hidden = decoder(
decoder_input, decoder_hidden, encoder_outputs
)
# Teacher forcing: next input is current target
decoder_input = target_variable[t].view(1, -1)
# Calculate and accumulate loss
mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t])
loss += mask_loss
print_losses.append(mask_loss.item() * nTotal)
n_totals += nTotal
else:
for t in range(max_target_len):
decoder_output, decoder_hidden = decoder(
decoder_input, decoder_hidden, encoder_outputs
)
# No teacher forcing: next input is decoder's own current output
_, topi = decoder_output.topk(1)
decoder_input = torch.LongTensor([[topi[i][0] for i in range(batch_size)]])
decoder_input = decoder_input.to(device)
# Calculate and accumulate loss
mask_loss, nTotal = maskNLLLoss(decoder_output, target_variable[t], mask[t])
loss += mask_loss
print_losses.append(mask_loss.item() * nTotal)
n_totals += nTotal
# Perform backpropatation
loss.backward()
# Clip gradients: gradients are modified in place
_ = nn.utils.clip_grad_norm_(encoder.parameters(), clip)
_ = nn.utils.clip_grad_norm_(decoder.parameters(), clip)
# Adjust model weights
encoder_optimizer.step()
decoder_optimizer.step()
return sum(print_losses) / n_totals