def test_sequencegenerator(self):
with tf.Graph().as_default():
text = "123456789101234567891012345678910123456789101234567891012345678910"
maxlen = 5
X, Y, char_idx = \
zqtflearn.data_utils.string_to_semi_redundant_sequences(text, seq_maxlen=maxlen, redun_step=3)
g = zqtflearn.input_data(shape=[None, maxlen, len(char_idx)])
g = zqtflearn.lstm(g, 32)
g = zqtflearn.dropout(g, 0.5)
g = zqtflearn.fully_connected(g, len(char_idx), activation='softmax')
g = zqtflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
learning_rate=0.1)
m = zqtflearn.SequenceGenerator(g, dictionary=char_idx,
seq_maxlen=maxlen,
clip_gradients=5.0)
m.fit(X, Y, validation_set=0.1, n_epoch=100, snapshot_epoch=False)
res = m.generate(10, temperature=.5, seq_seed="12345")
#self.assertEqual(res, "123456789101234", "SequenceGenerator test failed! Generated sequence: " + res + " expected '123456789101234'")
# Testing save method
m.save("test_seqgen.zqtflearn")
self.assertTrue(os.path.exists("test_seqgen.zqtflearn.index"))
# Testing load method
m.load("test_seqgen.zqtflearn")
res = m.generate(10, temperature=.5, seq_seed="12345")
def test_recurrent_layers(self):
X = [[1, 3, 5, 7], [2, 4, 8, 10], [1, 5, 9, 11], [2, 6, 8, 0]]
Y = [[0., 1.], [1., 0.], [0., 1.], [1., 0.]]
with tf.Graph().as_default():
g = zqtflearn.input_data(shape=[None, 4])
g = zqtflearn.embedding(g, input_dim=12, output_dim=4)
g = zqtflearn.lstm(g, 6)
g = zqtflearn.fully_connected(g, 2, activation='softmax')
g = zqtflearn.regression(g, optimizer='sgd', learning_rate=1.)
m = zqtflearn.DNN(g)
m.fit(X, Y, n_epoch=300, snapshot_epoch=False)
self.assertGreater(m.predict([[5, 9, 11, 1]])[0][1], 0.9)
def test_sequencegenerator_words(self):
with tf.Graph().as_default():
text = ["hello","world"]*100
word_idx = {"hello": 0, "world": 1}
maxlen = 2
vec = [x for x in map(word_idx.get, text) if x is not None]
sequences = []
next_words = []
for i in range(0, len(vec) - maxlen, 3):
sequences.append(vec[i: i + maxlen])
next_words.append(vec[i + maxlen])
X = np.zeros((len(sequences), maxlen, len(word_idx)), dtype=np.bool)
Y = np.zeros((len(sequences), len(word_idx)), dtype=np.bool)
for i, seq in enumerate(sequences):
for t, idx in enumerate(seq):
X[i, t, idx] = True
Y[i, next_words[i]] = True
g = zqtflearn.input_data(shape=[None, maxlen, len(word_idx)])
g = zqtflearn.lstm(g, 32)
g = zqtflearn.dropout(g, 0.5)
g = zqtflearn.fully_connected(g, len(word_idx), activation='softmax')
g = zqtflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
learning_rate=0.1)
m = zqtflearn.SequenceGenerator(g, dictionary=word_idx,
seq_maxlen=maxlen,
clip_gradients=5.0)
m.fit(X, Y, validation_set=0.1, n_epoch=100, snapshot_epoch=False)
res = m.generate(4, temperature=.5, seq_seed=["hello","world"])
res_str = " ".join(res[-2:])
self.assertEqual(res_str, "hello world", "SequenceGenerator (word level) test failed! Generated sequence: " + res_str + " expected 'hello world'")
# Testing save method
m.save("test_seqgen_word.zqtflearn")
self.assertTrue(os.path.exists("test_seqgen_word.zqtflearn.index"))
# Testing load method
m.load("test_seqgen_word.zqtflearn")
res = m.generate(4, temperature=.5, seq_seed=["hello","world"])
res_str = " ".join(res[-2:])
self.assertEqual(res_str, "hello world", "Reloaded SequenceGenerator (word level) test failed! Generated sequence: " + res_str + " expected 'hello world'")
n_words=10000,
valid_portion=0.1)
trainX, trainY = train
testX, testY = test
# Data preprocessing
# Sequence padding
trainX = pad_sequences(trainX, maxlen=100, value=0.)
testX = pad_sequences(testX, maxlen=100, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY)
testY = to_categorical(testY)
# Network building
net = zqtflearn.input_data([None, 100])
net = zqtflearn.embedding(net, input_dim=10000, output_dim=128)
net = zqtflearn.lstm(net, 128, dropout=0.8)
net = zqtflearn.fully_connected(net, 2, activation='softmax')
net = zqtflearn.regression(net,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy')
# Training
model = zqtflearn.DNN(net, tensorboard_verbose=0)
model.fit(trainX,
trainY,
validation_set=(testX, testY),
show_metric=True,
batch_size=32)
# NOTE: Padding is required for dimension consistency. This will pad sequences
# with 0 at the end, until it reaches the max sequence length. 0 is used as a
# masking value by dynamic RNNs in TFLearn; a sequence length will be
# retrieved by counting non zero elements in a sequence. Then dynamic RNN step
# computation is performed according to that length.
trainX = pad_sequences(trainX, maxlen=100, value=0.)
testX = pad_sequences(testX, maxlen=100, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY)
testY = to_categorical(testY)
# Network building
net = zqtflearn.input_data([None, 100])
# Masking is not required for embedding, sequence length is computed prior to
# the embedding op and assigned as 'seq_length' attribute to the returned Tensor.
net = zqtflearn.embedding(net, input_dim=10000, output_dim=128)
net = zqtflearn.lstm(net, 128, dropout=0.8, dynamic=True)
net = zqtflearn.fully_connected(net, 2, activation='softmax')
net = zqtflearn.regression(net,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy')
# Training
model = zqtflearn.DNN(net, tensorboard_verbose=0)
model.fit(trainX,
trainY,
validation_set=(testX, testY),
show_metric=True,
batch_size=32)
import zqtflearn
from zqtflearn.data_utils import *
path = "US_Cities.txt"
if not os.path.isfile(path):
context = ssl._create_unverified_context()
moves.urllib.request.urlretrieve("https://raw.githubusercontent.com/tflearn/tflearn.github.io/master/resources/US_Cities.txt", path, context=context)
maxlen = 20
string_utf8 = open(path, "r").read().decode('utf-8')
X, Y, char_idx = \
string_to_semi_redundant_sequences(string_utf8, seq_maxlen=maxlen, redun_step=3)
g = zqtflearn.input_data(shape=[None, maxlen, len(char_idx)])
g = zqtflearn.lstm(g, 512, return_seq=True)
g = zqtflearn.dropout(g, 0.5)
g = zqtflearn.lstm(g, 512)
g = zqtflearn.dropout(g, 0.5)
g = zqtflearn.fully_connected(g, len(char_idx), activation='softmax')
g = zqtflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
learning_rate=0.001)
m = zqtflearn.SequenceGenerator(g, dictionary=char_idx,
seq_maxlen=maxlen,
clip_gradients=5.0,
checkpoint_path='model_us_cities')
for i in range(40):
seed = random_sequence_from_string(string_utf8, maxlen)
m.fit(X, Y, validation_set=0.1, batch_size=128,
# -*- coding: utf-8 -*-
"""
MNIST Classification using RNN over images pixels. A picture is
representated as a sequence of pixels, coresponding to an image's
width (timestep) and height (number of sequences).
"""
from __future__ import division, print_function, absolute_import
import numpy as np
import zqtflearn
import zqtflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = np.reshape(X, (-1, 28, 28))
testX = np.reshape(testX, (-1, 28, 28))
net = zqtflearn.input_data(shape=[None, 28, 28])
net = zqtflearn.lstm(net, 128, return_seq=True)
net = zqtflearn.lstm(net, 128)
net = zqtflearn.fully_connected(net, 10, activation='softmax')
net = zqtflearn.regression(net, optimizer='adam',
loss='categorical_crossentropy', name="output1")
model = zqtflearn.DNN(net, tensorboard_verbose=2)
model.fit(X, Y, n_epoch=1, validation_set=0.1, show_metric=True,
snapshot_step=100)