lstm05.py

# Assume 26 unique characters
alphabet = ['a', 'b', ... , 'z']

# two sample sequences, inputs and targets
x = np.array(list('abc')) # inputs
y = np.array(list('xyz')) # targets

# define one-hot encoder and label encoder
onehot_encoder = OneHotEncoder(sparse=False).fit(alphabet)
label_encoder  = {ch: i for i, ch in enumerate(alphabet)}

# Use Cross Entropy Loss for classification problem
criterion = nn.CrossEntropyLoss()

# Transform input and targets
x = onehot_encoder.transform(x)
y = [label_encoder[ch] for ch in y]
y = torch.tensor(y)

# Define architecture:
input_size  = 50  # representing the one-hot encoded vector size
hidden_size = 100 # number of hidden nodes in the LSTM layer
n_layers    = 2   # number of LSTM layers
output_size = 50  # output of 50 scores for the next character

lstm   = nn.LSTM(input_size, hidden_size, n_layers, batch_first=True)
linear = nn.Linear(hidden_size, output_size)

# feed forward
x = get_batches(data)          # -> input x:    (batch_size, seq_length, num_features)
x, hs = lstm(x, hs)            # -> LSTM out:   (batch_size, seq_length, hidden_size)
x = x.reshape(-1, hidden_size) # -> Linear in:  (batch_size * seq_length, hidden_size)
x = linear(x)                  # -> Linear out: (batch_size * seq_length, out_size)

# calculate loss 
loss = criterion(x, y)