RNN_intro_2.py

# Lab 12 RNN
import torch
import torch.nn as nn

torch.manual_seed(777)  # reproducibility

#            0    1    2    3    4
idx2char = ['h', 'i', 'e', 'l', 'o']

# Teach hihell -> ihello
x_data = [0, 1, 0, 2, 3, 3]   # hihell
one_hot_lookup = [[1, 0, 0, 0, 0],  # 0
                  [0, 1, 0, 0, 0],  # 1
                  [0, 0, 1, 0, 0],  # 2
                  [0, 0, 0, 1, 0],  # 3
                  [0, 0, 0, 0, 1]]  # 4

y_data = [1, 0, 2, 3, 3, 4]    # ihello
x_one_hot = [one_hot_lookup[x] for x in x_data]

# As we have one batch of samples, we will change them to variables only once
inputs = torch.Tensor(x_one_hot)
labels = torch.LongTensor(y_data)

num_classes = 5
input_size = 5  # one-hot size
hidden_size = 5  # output from the RNN. 5 to directly predict one-hot
batch_size = 1   # one sentence
sequence_length = 1  # One by one
num_layers = 1  # one-layer rnn


class Model(nn.Module):

    def __init__(self):
        super(Model, self).__init__()
        self.rnn = nn.RNN(input_size=input_size,
                          hidden_size=hidden_size,
                          batch_first=True)

    def forward(self, hidden, x):
        # Reshape input (batch first)
        x = x.view(batch_size, sequence_length, input_size)

        # Propagate input through RNN
        # Input: (batch, seq_len, input_size)
        # hidden: (num_layers * num_directions, batch, hidden_size)
        out, hidden = self.rnn(x, hidden)
        return out.view(-1, num_classes), hidden

    def init_hidden(self):
        # Initialize hidden and cell states
        # (num_layers * num_directions, batch, hidden_size)
        return torch.zeros(num_layers, batch_size, hidden_size)


# Instantiate RNN model
model = Model()
print(model)

# Set loss and optimizer function
# CrossEntropyLoss = LogSoftmax + NLLLoss
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.1)

print(inputs.size(), labels.size())
# Train the model
for epoch in range(100):
    optimizer.zero_grad()
    loss = 0
    hidden = model.init_hidden()

    print("predicted string: ", end='')
    for input, label in zip(inputs, labels):
        output, hidden = model(hidden, input)
        val, idx = output.max(1)
        print(idx2char[idx.data[0]], end='')
        loss += criterion(output, label.reshape(-1))

    print(f', epoch: {epoch + 1}, loss: {loss.item():1.3f}')

    loss.backward()
    optimizer.step()

print("Learning finished!")