Created
September 5, 2017 06:20
-
-
Save schlerp/003c4ec1469e4d5f4da686f832dfabe2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from __future__ import absolute_import, division, print_function | |
import os | |
import pickle | |
from six.moves import urllib | |
import tflearn | |
from tflearn.data_utils import * | |
path = "data/sherlock_edited.txt" | |
char_idx_file = 'char_idx.pickle' | |
#if not os.path.isfile(path): | |
#urllib.request.urlretrieve("https://raw.githubusercontent.com/tflearn/tflearn.github.io/master/resources/shakespeare_input.txt", path) | |
maxlen = 25 | |
char_idx = None | |
if os.path.isfile(char_idx_file): | |
print('Loading previous char_idx') | |
char_idx = pickle.load(open(char_idx_file, 'rb')) | |
X, Y, char_idx = \ | |
textfile_to_semi_redundant_sequences(path, seq_maxlen=maxlen, redun_step=3) | |
pickle.dump(char_idx, open(char_idx_file,'wb')) | |
# input | |
i = tflearn.input_data([None, maxlen, len(char_idx)]) | |
# path a | |
a = tflearn.conv_1d(i, 16, 10) | |
a = tflearn.lstm(a, 16, return_seq=True) | |
a = tflearn.dropout(a, 0.5) | |
a = tflearn.gru(a, 32) | |
a = tflearn.dropout(a, 0.5) | |
# path b | |
b = tflearn.lstm(i, 48, return_seq=True) | |
b = tflearn.dropout(b, 0.5) | |
b = tflearn.gru(b, 64) | |
b = tflearn.dropout(b, 0.5) | |
# path c | |
c = tflearn.lstm(i, 96, return_seq=True) | |
c = tflearn.dropout(c, 0.5) | |
c = tflearn.gru(c, 128) | |
c = tflearn.dropout(c, 0.5) | |
# merge | |
m = tflearn.merge_outputs([a, b, c]) | |
# fully connected | |
fc = tflearn.highway(m, 224, activation='relu') | |
fc = tflearn.dropout(fc, 0.5) | |
fc = tflearn.fully_connected(fc, len(char_idx), activation='softmax') | |
fc = tflearn.regression(fc, optimizer='adam', loss='categorical_crossentropy', | |
learning_rate=0.002) | |
# final model | |
m = tflearn.SequenceGenerator(fc, dictionary=char_idx, | |
seq_maxlen=maxlen, | |
clip_gradients=5.0, | |
checkpoint_path='model_aiw', | |
tensorboard_verbose=1) | |
for i in range(10): | |
seed = random_sequence_from_textfile(path, maxlen) | |
m.fit(X, Y, validation_set=0.1, batch_size=128, | |
n_epoch=1, run_id='aiw') | |
print("-- TESTING...") | |
print("-- Test with temperature of 1.0 --") | |
print(m.generate(600, temperature=1.0, seq_seed=seed)) | |
print("-- Test with temperature of 0.5 --") | |
print(m.generate(600, temperature=0.5, seq_seed=seed)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment