model.train(X, y, num_epochs=1)
start_index = random.randint(0, len(text) - maxlen - 1)
for diversity in [0.2, 0.5, 1.0, 1.2]:
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(400):
x = np.zeros((1, maxlen, len(chars)))
for t, char in enumerate(sentence):
x[0, t, char_indices[char]] = 1.
preds = model.predict(x)[0]
next_index = sample(preds, diversity)
next_char = indices_char[next_index]
generated += next_char
sentence = sentence[1:] + next_char
sys.stdout.write(next_char)
sys.stdout.flush()
print()
ok.save_model(model)
return np.argmax(np.random.multinomial(1, a, 1))
# train the model, output generated text after each iteration
for iteration in range(1, 60):
print()
print('-' * 50)
print('Iteration', iteration)
model.fit(X, y, batch_size=128, nb_epoch=1)'''
def sample(a, temperature=1.0):
a = np.log(a) / temperature
a = np.exp(a) / np.sum(np.exp(a))
return np.argmax(np.random.multinomial(1, a, 1))
model = ok.load_model('keras_shakespeare_model.pk')
start_index = random.randint(0, len(text) - maxlen - 1)
diversity = 0.5
generated = ''
sentence = text[start_index: start_index + maxlen]
generated += sentence
sys.stdout.write(generated)
for iteration in range(400):
x = np.zeros((1, maxlen, len(chars)))
for t, char in enumerate(sentence):
x[0, t, char_indices[char]] = 1.
preds = model.predict(x, verbose=0)[0]
next_index = sample(preds, diversity)
try:
next_index = sample(preds, diversity)
next_char = indices_char[next_index]
generated += next_char
sentence = sentence[1:] + next_char
sys.stdout.write(next_char)
sys.stdout.flush()
except ValueError:
print("Value Error")
model.train(X_train, y_train, num_epochs=num_epochs,
epoch_callback=predict)
end_time_1 = time.clock()
t1 = end_time_1 - start_time_1
ok.save_model(model)
del model
model = ok.load_model()
model.reinforce(X_train, y_train, num_epochs=num_epochs,
epoch_callback=predict)
'''start_time_2 = time.clock()
model_keras = Sequential()
model_keras.add(GRU(h_layer_size, input_dim=len(chars),
init='normal', return_sequences=False))
model_keras.add(BatchNormalization(mode=1))
model_keras.add(PReLU())
model_keras.add(Dropout(dropout_p))
model_keras.add(Dense(d_layer_size, init='normal'))
model_keras.add(BatchNormalization(mode=1))
