iter = 0
header = ' Time Epoch Iteration Loss Train/Acc. Val/Acc.'
print(header)
log_template = ' '.join('{:>6.0f},{:>5.0f},{:>9.0f},{:>9.6f}'.split(','))
dev_log_template = ' '.join(
'{:>6.0f},{:>5.0f},{:>9.0f},{:>9.6f},{:9.6f},{:11.6f}'.split(','))
model.train()
for epoch in range(args.epochs):
# shuffle the dataset and create batches (truncate the last batch if not of equal size)
shuffled_indices = np.random.permutation(len(train_set))
num_batches = len(shuffled_indices) // args.batch_size
batch_indices = np.split(
shuffled_indices,
range(args.batch_size, len(shuffled_indices), args.batch_size))
model.hidden = model.init_hidden()
for batch_ix in range(num_batches):
iter += 1
batch = train_set[batch_indices[batch_ix]]
inputs, targets = data.create_tensorized_batch(batch, max_sent_length,
w2v_map, label_to_ix)
# print("inputs size: {}".format(inputs.size()))
# print("targets size: {}".format(targets.size()))
# clear out gradients and hidden states of the model
model.zero_grad()
model.hidden = repackage_hidden(model.hidden)
# prepare inputs for LSTM model and run forward pass
scores = model(inputs)
print('Character to id:\n', char2id)
print("Distinct boys' name count:\n", len(boy_names))
model = BiLSTM(input_size=len(char2id), hidden_size=args.hidden_size, output_size=len(char2id))
loss_func = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=args.lr)
batch_size = args.batch_size
avg_loss = 0
for epoch in range(args.num_epoch):
batches = yield_batch(boy_names, batch_size, char2id)
for i, (input_, target_, seq_lengths) in enumerate(batches):
loss = 0
seq_len = len(input_[:, 0])
batch_size_ = len(input_[0, :])
hidden = model.init_hidden(batch_size_)
model.zero_grad()
for x in range(seq_len):
output, hidden = model(input_[x, :], hidden)
loss += loss_func(output, target_[x, :])
loss.backward()
optimizer.step()
avg_loss += (loss.item() / seq_len)
if i % 100 == 0:
print('epoch: {}, batch: {}, loss: {}'.format(epoch, i, loss.item()))
torch.save(model, './name.pt')
