def do_birnn_wordbag(trainX, testX, trainY, testY):
y_test=testY
#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, nb_classes=2)
testY = to_categorical(testY, nb_classes=2)
# Network building
# Network building
net = input_data(shape=[None, 100])
net = tflearn.embedding(net, input_dim=10000, output_dim=128)
net = tflearn.bidirectional_rnn(net, BasicLSTMCell(128), BasicLSTMCell(128))
net = dropout(net, 0.5)
net = fully_connected(net, 2, activation='softmax')
net = regression(net, optimizer='adam', loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, tensorboard_verbose=0)
model.fit(trainX, trainY, validation_set=(testX, testY), show_metric=True,
batch_size=1,run_id="uba",n_epoch=10)
y_predict_list = model.predict(testX)
#print y_predict_list
y_predict = []
for i in y_predict_list:
#print i[0]
if i[0] >= 0.5:
y_predict.append(0)
else:
y_predict.append(1)
print(classification_report(y_test, y_predict))
print metrics.confusion_matrix(y_test, y_predict)
def model(self,
type=None,
mode="train",
num_layers=2,
state_size=32,
learning_rate=0.001,
tensorboard_verbose=3):
net = tflearn.input_data(shape=[None, 9])
net = tflearn.embedding(net,
input_dim=21,
output_dim=32,
weights_init='xavier')
if type == 'bi_rnn':
out_rnn = tflearn.bidirectional_rnn(net, tflearn.BasicLSTMCell(32),
tflearn.BasicLSTMCell(32))
elif type == 'basic_lstm':
for i in range(4):
net = tflearn.lstm(net, n_units=40, return_seq=True)
#net = tflearn.lstm(net, n_units=40, return_seq=True)
out_rnn = tflearn.lstm(net, n_units=40, return_seq=False)
elif type == 'basic_rnn':
out_rnn = tflearn.simple_rnn(net, 40)
else:
out_rnn = net
net = tflearn.fully_connected(out_rnn, 100, activation='prelu')
net = tflearn.layers.normalization.batch_normalization(net)
net = tflearn.dropout(net, 0.1)
net = tflearn.fully_connected(net, 1, activation='sigmoid')
"""
single_cell = getattr(tf.contrib.rnn, cell_type)(cell_size, state_is_tuple=True)
if num_layers == 1:
cell = single_cell
else:
cell = tf.contrib.rnn.MultiRNNCell([single_cell] * num_layers)
"""
with tf.name_scope(
"TargetsData"
): # placeholder for target variable (i.e. trainY input)
targetY = tf.placeholder(shape=[None, 1],
dtype=tf.float32,
name="Y")
network = tflearn.regression(net,
placeholder=targetY,
optimizer=self.optimizer(learning_rate),
learning_rate=learning_rate,
loss=tflearn.mean_square(net, targetY),
metric=self.accuracy(net, targetY),
name='no rnn')
model = tflearn.DNN(network, tensorboard_verbose=tensorboard_verbose)
return model
def build_model(vocabFile, model_type='bilstm'):
processor = VocabularyProcessor.restore(vocabFile)
n_words = len(processor.vocabulary_)
net = tflearn.input_data([None, 300])
net = tflearn.embedding(net, input_dim=n_words, output_dim=200)
if model_type == 'bilstm':
net = tflearn.bidirectional_rnn(net, tflearn.BasicLSTMCell(200),
tflearn.BasicLSTMCell(200))
net = dropout(net, 0.5)
elif model_type == 'lstm':
net = tflearn.lstm(net, 200, dropout=0.5)
net = dropout(net, 0.5)
elif model_type == 'cnn':
net = conv_model(net)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net,
optimizer='adam',
learning_rate=0.05,
loss='categorical_crossentropy')
return net
def build_net3():
"""Bidirectional RNN"""
net = tflearn.input_data(shape=[None, time_window, 1])
lstm1 = tflearn.BasicLSTMCell(num_units=lstm_units)
lstm2 = tflearn.BasicLSTMCell(num_units=lstm_units)
#net = tflearn.fully_connected(net, 10, activation='sigmoid')
#net = tflearn.reshape(net, [-1, 10, 1])
#net = tflearn.lstm(net, dropout=(1.0, 0.5), n_units=lstm_units, return_seq=True)
net = tflearn.bidirectional_rnn(net, lstm1, lstm2, return_seq=False)
#net = tflearn.fully_connected(net, 5, activation='linear')
#net = tflearn.dropout(net, 0.5)
#net = tflearn.fully_connected(net, lstm_units, activation='relu')
#net = tflearn.dropout(net, 0.5)
#For model 2
net = tflearn.fully_connected(net, predict_steps+1, activation='linear')
#For model 1 and 3
#net = tflearn.fully_connected(net, 1, activation='linear')
#For model 4
#net = tflearn.fully_connected(net, 3, activation='softmax')
#net = tflearn.regression(net, metric='accuracy', optimizer=optimizer,
#loss='categorical_crossentropy',
#learning_rate=learn_rate, shuffle_batches=False)
net = tflearn.regression(net, metric=None, optimizer=optimizer, loss='mean_square',
learning_rate=learn_rate, shuffle_batches=False)
model = tflearn.DNN(net, clip_gradients=0.0, tensorboard_verbose=0)
return model
def bi_lstm(trainX, trainY, testX, testY):
trainX = pad_sequences(trainX, maxlen=200, value=0.)
testX = pad_sequences(testX, maxlen=200, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY, nb_classes=2)
testY = to_categorical(testY, nb_classes=2)
# Network building
net = tflearn.input_data(shape=[None, 200])
net = tflearn.embedding(net, input_dim=20000, output_dim=128)
net = tflearn.bidirectional_rnn(net, BasicLSTMCell(128),
BasicLSTMCell(128))
net = tflearn.dropout(net, 0.5)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net,
optimizer='adam',
loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
model.fit(trainX,
trainY,
validation_set=0.1,
show_metric=True,
batch_size=64,
run_id="rnn-bilstm")
def simple_blstm(): input_layer = tf.input_data(shape=[None, 5, 19]) model = tf.bidirectional_rnn(input_layer, tf.BasicLSTMCell(91), tf.BasicLSTMCell(91)) model = tf.dropout(model, 0.5) model = tf.fully_connected(model, 11, activation='sigmoid') sgd = tf.SGD(learning_rate=0.01, lr_decay=0.96, decay_step=1000) model = tf.regression(model, optimizer=sgd, loss='categorical_crossentropy') return tf.DNN(model, clip_gradients=0., tensorboard_verbose=0)
def run():
net = tflearn.input_data([None, 100])
net = tflearn.embedding(net, input_dim=20000, output_dim=128)
net = tflearn.bidirectional_rnn(
net, tflearn.BasicLSTMCell(128), tflearn.BasicLSTMCell(128))
net = tflearn.dropout(net, 0.5)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(
net, optimizer='adam', loss='categorical_crossentropy')
m = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
m.fit(trainX, trainY, validation_set=0.1, show_metric=True, batch_size=64)
m.save('models/bidirectional_rnn.tfl')
def bi_lstm(trainX, trainY,testX, testY):
trainX = pad_sequences(trainX, maxlen=200, value=0.)
testX = pad_sequences(testX, maxlen=200, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY, nb_classes=2)
testY = to_categorical(testY, nb_classes=2)
# Network building
net = tflearn.input_data(shape=[None, 200])
net = tflearn.embedding(net, input_dim=20000, output_dim=128)
net = tflearn.bidirectional_rnn(net, BasicLSTMCell(128), BasicLSTMCell(128))
net = tflearn.dropout(net, 0.5)
net = tflearn.fully_connected(net, 2, activation='softmax')
net = tflearn.regression(net, optimizer='adam', loss='categorical_crossentropy')
# Training
model = tflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
model.fit(trainX, trainY, validation_set=0.1, show_metric=True, batch_size=64,run_id="rnn-bilstm")
def add_deep_layers(self, net, model_type, out_embedding_dim, layer_size, n_layers):
if model_type == 'embedding_rnn':
out_rnn = tflearn.embedding(net, input_dim=21, output_dim=out_embedding_dim, weights_init='xavier')
elif model_type == 'bi_rnn':
out_rnn = tflearn.bidirectional_rnn(net, tflearn.BasicLSTMCell(layer_size), tflearn.BasicLSTMCell(layer_size))
elif model_type == 'deep_rnn':
for i in range(n_layers):
net = tflearn.lstm(net, n_units=layer_size, return_seq=True)
out_rnn = tflearn.lstm(net, layer_size)
elif model_type == 'basic_rnn':
out_rnn = tflearn.simple_rnn(net, layer_size)
else:
out_rnn = net
return out_rnn
# X, Y, char_idx = \
# textfile_to_semi_redundant_sequences(path, seq_maxlen=maxlen, redun_step=3)
# TODO - What do these look like?
# print(X)
# print(Y)
# Saves our dictionary for later use
pickle.dump(char_idx, open(char_idx_file, 'wb'))
# New
g = tflearn.input_data([None, maxlen, len(char_idx)])
# g = tflearn.fully_connected(g, len(char_idx), activation='softmax')
# g = tflearn.embedding(g, 10000, 342)
g = tflearn.bidirectional_rnn(g,
tflearn.BasicLSTMCell(342),
tflearn.BasicLSTMCell(342),
dynamic=True)
g = tflearn.dropout(g, 0.5)
g = tflearn.fully_connected(g, len(char_idx), activation='softmax')
g = tflearn.regression(g,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Old
# g = tflearn.input_data([None, maxlen, len(char_idx)])
# g = tflearn.lstm(g, 512, return_seq=True)
# g = tflearn.dropout(g, 0.5)
# g = tflearn.lstm(g, 512, return_seq=True)
# g = tflearn.dropout(g, 0.5)
# g = tflearn.lstm(g, 512)