def test_vbs1(self):
with tf.Graph().as_default():
# Data loading and preprocessing
import zqtflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])
X = X[:20, :, :, :]
Y = Y[:20, :]
testX = testX[:10, :, :, :]
testY = testY[:10, :]
# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network,
32,
3,
activation='relu',
regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network,
64,
3,
activation='relu',
regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 10, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='target')
# Training
model = zqtflearn.DNN(network, tensorboard_verbose=3)
model.fit({'input': X}, {'target': Y},
n_epoch=1,
batch_size=10,
validation_set=({
'input': testX
}, {
'target': testY
}),
validation_batch_size=5,
snapshot_step=10,
show_metric=True,
run_id='convnet_mnist_vbs')
self.assertEqual(model.train_ops[0].validation_batch_size, 5)
self.assertEqual(model.train_ops[0].batch_size, 10)
def make_core_network(network):
network = zqtflearn.reshape(network, [-1, 28, 28, 1], name="reshape")
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 10, activation='softmax')
return network
def test_vm1(self):
with tf.Graph().as_default():
# Data loading and preprocessing
import zqtflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])
X = X[:10, :, :, :]
Y = Y[:10, :]
# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network,
32,
3,
activation='relu',
regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network,
64,
3,
activation='relu',
regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
# construct two varaibles to add as additional "valiation monitors"
# these varaibles are evaluated each time validation happens (eg at a snapshot)
# and the results are summarized and output to the tensorboard events file,
# together with the accuracy and loss plots.
#
# Here, we generate a dummy variable given by the sum over the current
# network tensor, and a constant variable. In practice, the validation
# monitor may present useful information, like confusion matrix
# entries, or an AUC metric.
with tf.name_scope('CustomMonitor'):
test_var = tf.reduce_sum(tf.cast(network, tf.float32),
name="test_var")
test_const = tf.constant(32.0, name="custom_constant")
print("network=%s, test_var=%s" % (network, test_var))
network = fully_connected(network, 10, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='target',
validation_monitors=[test_var, test_const])
# Training
model = zqtflearn.DNN(network, tensorboard_verbose=3)
model.fit({'input': X}, {'target': Y},
n_epoch=1,
validation_set=({
'input': testX
}, {
'target': testY
}),
snapshot_step=10,
show_metric=True,
run_id='convnet_mnist')
# check for validation monitor variables
ats = tf.get_collection("Adam_testing_summaries")
print("ats=%s" % ats)
self.assertTrue(
len(ats) == 4
) # should be four variables being summarized: [loss, test_var, test_const, accuracy]
session = model.session
print("session=%s" % session)
trainer = model.trainer
print("train_ops = %s" % trainer.train_ops)
top = trainer.train_ops[0]
vmtset = top.validation_monitors_T
print("validation_monitors_T = %s" % vmtset)
with model.session.as_default():
ats_var_val = zqtflearn.variables.get_value(vmtset[0])
ats_const_val = zqtflearn.variables.get_value(vmtset[1])
print("summary values: var=%s, const=%s" %
(ats_var_val, ats_const_val))
self.assertTrue(
ats_const_val ==
32) # test to make sure the constant made it through
net = relu(
batch_normalization(
conv_2d(net,
1536,
1,
bias=False,
activation=None,
name='Conv2d_7b_1x1')))
net = avg_pool_2d(net,
net.get_shape().as_list()[1:3],
strides=2,
padding='VALID',
name='AvgPool_1a_8x8')
net = flatten(net)
net = dropout(net, dropout_keep_prob)
loss = fully_connected(net, num_classes, activation='softmax')
network = zqtflearn.regression(loss,
optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = zqtflearn.DNN(network,
checkpoint_path='inception_resnet_v2',
max_checkpoints=1,
tensorboard_verbose=2,
tensorboard_dir="./tflearn_logs/")
model.fit(X,
Y,
n_epoch=1000,
validation_set=0.1,
branch2 = conv_1d(network,
128,
4,
padding='valid',
activation='relu',
regularizer="L2")
branch3 = conv_1d(network,
128,
5,
padding='valid',
activation='relu',
regularizer="L2")
network = merge([branch1, branch2, branch3], mode='concat', axis=1)
network = tf.expand_dims(network, 2)
network = global_max_pool(network)
network = dropout(network, 0.5)
network = fully_connected(network, 2, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='target')
# Training
model = zqtflearn.DNN(network, tensorboard_verbose=0)
model.fit(trainX,
trainY,
n_epoch=5,
shuffle=True,
validation_set=(testX, testY),
show_metric=True,
batch_size=32)
# Data loading and preprocessing
import zqtflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])
# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 10, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='target')
# Training
model = zqtflearn.DNN(network, tensorboard_verbose=0)
model.fit({'input': X}, {'target': Y},
n_epoch=20,
validation_set=({
'input': testX
from zqtflearn.layers.embedding_ops import embedding
from zqtflearn.layers.recurrent import bidirectional_rnn, BasicLSTMCell
from zqtflearn.layers.estimator import regression
# IMDB Dataset loading
train, test, _ = imdb.load_data(path='imdb.pkl',
n_words=10000,
valid_portion=0.1)
trainX, trainY = train
testX, testY = test
# Data preprocessing
# Sequence padding
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)
testY = to_categorical(testY)
# Network building
net = input_data(shape=[None, 200])
net = embedding(net, input_dim=20000, output_dim=128)
net = 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 = zqtflearn.DNN(net, clip_gradients=0., tensorboard_verbose=2)
model.fit(trainX, trainY, validation_set=0.1, show_metric=True, batch_size=64)
activation='relu',
name='block5_conv2')
block5_conv3 = conv_2d(block5_conv2,
512,
3,
activation='relu',
name='block5_conv3')
block5_conv4 = conv_2d(block5_conv3,
512,
3,
activation='relu',
name='block5_conv4')
block4_pool = max_pool_2d(block5_conv4, 2, strides=2, name='block4_pool')
flatten_layer = zqtflearn.layers.core.flatten(block4_pool, name='Flatten')
fc1 = fully_connected(flatten_layer, 4096, activation='relu')
dp1 = dropout(fc1, 0.5)
fc2 = fully_connected(dp1, 4096, activation='relu')
dp2 = dropout(fc2, 0.5)
network = fully_connected(dp2, 1000, activation='rmsprop')
regression = zqtflearn.regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
model = zqtflearn.DNN(regression,
checkpoint_path='vgg19',
tensorboard_dir="./logs")
inception_5b_pool = max_pool_2d(inception_5a_output,
kernel_size=3,
strides=1,
name='inception_5b_pool')
inception_5b_pool_1_1 = conv_2d(inception_5b_pool,
128,
filter_size=1,
activation='relu',
name='inception_5b_pool_1_1')
inception_5b_output = merge([
inception_5b_1_1, inception_5b_3_3, inception_5b_5_5, inception_5b_pool_1_1
],
axis=3,
mode='concat')
pool5_7_7 = avg_pool_2d(inception_5b_output, kernel_size=7, strides=1)
pool5_7_7 = dropout(pool5_7_7, 0.4)
# fc
loss = fully_connected(pool5_7_7, 17, activation='softmax')
network = regression(loss,
optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
# to train
model = zqtflearn.DNN(network,
checkpoint_path='model_googlenet',
max_checkpoints=1,
tensorboard_verbose=2)
model.fit(X,
