Function train

examples/rnn/char_rnn.py:212–240

(data,
          max_epoch,
          hidden_size=100,
          seq_length=100,
          batch_size=16,
          model_path='model')

def train(data,
          max_epoch,
          hidden_size=100,
          seq_length=100,
          batch_size=16,
          model_path='model'):
    # SGD with L2 gradient normalization
    cuda = device.create_cuda_gpu()
    model = CharRNN(data.vocab_size, hidden_size)
    model.graph(True, False)

    inputs, labels = None, None

    for epoch in range(max_epoch):
        model.train()
        train_loss = 0
        for b in tqdm(range(data.num_train_batch)):
            batch = data.train_dat[b * batch_size:(b + 1) * batch_size]
            inputs, labels = convert(batch, batch_size, seq_length,
                                     data.vocab_size, cuda, inputs, labels)
            out, loss = model(inputs, labels)
            model.reset_states(cuda)
            train_loss += tensor.to_numpy(loss)[0]

        print('\nEpoch %d, train loss is %f' %
              (epoch, train_loss / data.num_train_batch / seq_length))

        evaluate(model, data, batch_size, seq_length, cuda, inputs, labels)
        sample(model, data, cuda)


if __name__ == '__main__':