RNN_intro_3.py

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

torch.manual_seed(777)  # reproducibility


idx2char = ['h', 'i', 'e', 'l', 'o']

# Teach hihell -> ihello
x_data = [[0, 1, 0, 2, 3, 3]]   # hihell
x_one_hot = [[[1, 0, 0, 0, 0],   # h 0
              [0, 1, 0, 0, 0],   # i 1
              [1, 0, 0, 0, 0],   # h 0
              [0, 0, 1, 0, 0],   # e 2
              [0, 0, 0, 1, 0],   # l 3
              [0, 0, 0, 1, 0]]]  # l 3

y_data = [1, 0, 2, 3, 3, 4]    # ihello

# 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 LSTM. 5 to directly predict one-hot
batch_size = 1   # one sentence
sequence_length = 6  # |ihello| == 6
num_layers = 1  # one-layer rnn


class RNN(nn.Module):

    def __init__(self, num_classes, input_size, hidden_size, num_layers):
        super(RNN, self).__init__()

        self.num_classes = num_classes
        self.num_layers = num_layers
        self.input_size = input_size
        self.hidden_size = hidden_size
        self.sequence_length = sequence_length

        self.rnn = nn.RNN(input_size=self.input_size, 
                          hidden_size=self.hidden_size,
                          batch_first=True)

    def forward(self, x):
        # Initialize hidden and cell states
        # (num_layers * num_directions, batch, hidden_size) for batch_first=True
        h_0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size)

        # Propagate input through RNN
        # Input: (batch, seq_len, input_size)
        # h_0: (num_layers * num_directions, batch, hidden_size)

        out, _ = self.rnn(x, h_0)
        return out.view(-1, self.num_classes)


# Instantiate RNN model
rnn = RNN(num_classes, input_size, hidden_size, num_layers)
print(rnn)

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

# Train the model
for epoch in range(100):
    outputs = rnn(inputs)
    optimizer.zero_grad()
    loss = criterion(outputs, labels)
    loss.backward()
    optimizer.step()
    _, idx = outputs.max(1)
    idx = idx.data.numpy()
    result_str = ''.join(idx2char[c] for c in idx.squeeze())
    print(f'epoch: {epoch + 1}, loss: {loss.item():1.3f}')
    print("Predicted string: ", result_str)

print("Learning finished!")