def generate(net, seed_string='A', predict_length=100, temperature=0.8, cuda=None):
hidden = net.init_hidden(1, cuda=cuda)
if cuda is not None:
prime_input = Variable(common.char_tensor(seed_string).unsqueeze(0).cuda(device=cuda))
else:
prime_input = Variable(common.char_tensor(seed_string).unsqueeze(0))
# Use seed string to "build up" hidden state
predicted = seed_string
for p in range(len(seed_string) - 1):
_, hidden = net(prime_input[:, p], hidden)
inp = prime_input[:, -1]
for p in range(predict_length):
output, hidden = net(inp, hidden)
# Sample from the network as a multinomial distribution
output_dist = output.data.view(-1).div(temperature).exp()
top_i = torch.multinomial(output_dist, 1)[0]
# Add predicted character to string and use as next input
predicted_char = common.trainable_characters[top_i]
predicted += predicted_char
if cuda is not None:
inp = mythic_model_character.Variable(common.char_tensor(predicted_char).unsqueeze(0).cuda(cuda))
else:
inp = mythic_model_character.Variable(common.char_tensor(predicted_char).unsqueeze(0))
return predicted
def generate(decoder, seed_string='A', predict_length=100, temperature=0.8, cuda=False):
hidden = decoder.init_hidden(1)
prime_input = mythic_model_character.Variable(common.char_tensor(seed_string).unsqueeze(0))
if cuda:
hidden = hidden.cuda()
prime_input = prime_input.cuda()
predicted = seed_string
# Use priming string to "build up" hidden state
for p in range(len(seed_string) - 1):
_, hidden = decoder(prime_input[:, p], hidden)
inp = prime_input[:, -1]
for p in range(predict_length):
output, hidden = decoder(inp, hidden)
# Sample from the network as a multinomial distribution
output_dist = output.data.view(-1).div(temperature).exp()
top_i = torch.multinomial(output_dist, 1)[0]
# Add predicted character to string and use as next input
predicted_char = common.trainable_characters[top_i]
predicted += predicted_char
inp = mythic_model_character.Variable(common.char_tensor(predicted_char).unsqueeze(0))
if cuda:
inp = inp.cuda()
return predicted
def random_training_set():
inp = model.torch.LongTensor(settings.batch_size, settings.chunk_size)
target = model.torch.LongTensor(settings.batch_size, settings.chunk_size)
for bi in range(settings.batch_size):
start_index = random.randint(
0, settings.text_length - settings.chunk_size - 1)
end_index = start_index + settings.chunk_size + 1
chunk = settings.text_string[start_index:end_index]
inp[bi] = common.char_tensor(chunk[:-1])
target[bi] = common.char_tensor(chunk[1:])
inp = model.Variable(inp)
target = model.Variable(target)
if settings.cuda is not None:
inp = inp.cuda()
target = target.cuda()
return inp, target
def ordered_training_set(start_index):
if start_index > (settings.text_length - settings.chunk_size):
log.out.warning(
"Requested index would blow bounds in text array, setting to random."
)
start_index = random.randint(
0, settings.text_length - settings.chunk_size)
inp = model.torch.LongTensor(settings.batch_size, settings.chunk_size)
target = model.torch.LongTensor(settings.batch_size, settings.chunk_size)
for bi in range(settings.batch_size):
# start_index = random.randint(0, settings.text_length - settings.chunk_size)
end_index = start_index + settings.chunk_size + 1
chunk = settings.text_string[start_index:end_index]
inp[bi] = common.char_tensor(chunk[:-1])
target[bi] = common.char_tensor(chunk[1:])
inp = model.Variable(inp)
target = model.Variable(target)
if settings.cuda:
inp = inp.cuda()
target = target.cuda()
return inp, target, end_index