def main_okapi():
import OkapiV2.Core as ok
from OkapiV2.Core import Model
from OkapiV2.Layers.Basic import FullyConnected, Dropout, BatchNorm
from OkapiV2.Layers.Activations import ActivationLayer, PReLULayer
from OkapiV2.Layers.Recurrent import LSTM
from OkapiV2 import Activations, Optimizers, Losses
path = 'data/lear.txt'
text = open(path).read().lower() # [0:corpus_length]
print('Corpus length:', len(text))
chars = set(text)
print('Total Characters:', len(chars))
char_to_index = dict((c, i) for i, c in enumerate(chars))
index_to_char = dict((i, c) for i, c in enumerate(chars))
# cut the text in semi-redundant sequences of maxlen characters
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
sentences.append(text[i: i + maxlen])
next_chars.append(text[i + maxlen])
print('Total Sequences:', len(sentences))
print('Vectorization...')
X = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
y = np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):
for t, char in enumerate(sentence):
X[i, t, char_to_index[char]] = 1
y[i, char_to_index[next_chars[i]]] = 1
def sample(a, temperature=1.0):
# helper function to sample an index from a probability array
a = np.log(a) / temperature
a = np.exp(a) / np.sum(np.exp(a)) - 1e-7
return np.argmax(np.random.multinomial(1, a, 1))
model = Model()
model.add(LSTM((h_layer_size, 1, 1, 1)))
model.add(PReLULayer())
model.add(Dropout(0.2))
model.add(BatchNorm())
model.add(LSTM((h_layer_size, 1, 1, 1)))
model.add(PReLULayer())
model.add(Dropout(0.2))
model.add(BatchNorm())
model.add(FullyConnected())
model.add(ActivationLayer(Activations.alt_softmax))
model.set_loss(Losses.Crossentropy())
model.set_optimizer(Optimizers.RMSprop(learning_rate=learning_rate))
for iteration in range(0, num_iterations):
print()
print('-' * 50)
print('Iteration', iteration + 1)
model.train(X, y, batch_size=batch_size, num_epochs=1,
params_filename='okapi_shakespeare_params.pk')
start_index = random.randint(0, len(text) - maxlen - 1)
for diversity in diversities:
print()
print('----- diversity:', diversity)
generated = ''
sentence = text[start_index: start_index + maxlen]
generated += sentence
print('----- Generating with seed: "' + sentence + '"')
sys.stdout.write(generated)
for iteration in range(num_chars):
x = np.zeros((1, maxlen, len(chars)))
for t, char in enumerate(sentence):
x[0, t, char_to_index[char]] = 1.
preds = model.predict(x)
preds = preds[0]
next_index = sample(preds, diversity)
next_char = index_to_char[next_index]
generated += next_char
sentence = sentence[1:] + next_char
sys.stdout.write(next_char)
sys.stdout.flush()
print()
ok.save_model(model, 'okapi_shakespeare_model.pk')
