def get_network():
# input images
network = input_data(shape=[None,33,33,4], name='input')
# local pathway [conv + pool + norm]
#path1 = conv_2d(network, 32, 7, activation='relu', regularizer="L2", padding='valid')
path1 = conv_2d(network, 64, 7, activation='relu', regularizer="L2", padding='valid')
path1 = max_pool_2d(path1, 4, 1, padding='valid')
path1 = dropout(path1, 0.5)
#path1 = local_response_normalization(path1)
#path1 = conv_2d(path1, 32, 3, activation='relu', regularizer="L2", padding='valid')
path1 = conv_2d(path1, 64, 3, activation='relu', regularizer="L2", padding='valid')
path1 = max_pool_2d(path1, 2, 1, padding='valid')
path1 = dropout(path1, 0.5)
#path1 = local_response_normalization(path1)
# global pathway
#path2 = conv_2d(network, 80, 13, activation='relu', regularizer="L2", padding='valid')
path2 = conv_2d(network, 160, 13, activation='relu', regularizer="L2", padding='valid')
path2 = dropout(path2, 0.5)
#path2 = local_response_normalization(path2)
network = merge([path1,path2],'concat',axis=3)
network = conv_2d(network, 5, 21, activation='relu', regularizer="L2")
network = flatten(network, name="flatten")
# softmax + output layers
network = fully_connected(network, 5, activation='softmax', name='soft')
network = regression(network, optimizer='adam', learning_rate=0.00005, # 0.0001
loss='categorical_crossentropy', name='target', batch_size=500)
return network
def neural_network_model4(IMG_SIZE, LR):
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 64, (5, 5), activation='relu')
convnet = max_pool_2d(convnet, (5, 5), strides=(2, 2))
convnet = conv_2d(convnet, 64, (3, 3), activation='relu')
convnet = conv_2d(convnet, 64, (3, 3), activation='relu')
convnet = avg_pool_2d(convnet, (3, 3), strides=(2, 2))
convnet = dropout(convnet, 0.7)
convnet = conv_2d(convnet, 128, (3, 3), activation='relu')
convnet = conv_2d(convnet, 128, (3, 3), activation='relu')
convnet = avg_pool_2d(convnet, (3, 3), strides=(2, 2))
convnet = dropout(convnet, 0.7)
convnet = flatten(convnet)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.7)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.7)
convnet = fully_connected(convnet, 7, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
learning_rate=LR,
loss='categorical_crossentropy',
name='targets')
convnet = dropout(convnet, 0.7)
model = tflearn.DNN(convnet, tensorboard_dir='log')
return model
def create_model():
print("Building CNN")
network = input_data(shape=[None, 48, 48, 1])
#print("Input Data",network.shape[1:])
network = conv_2d(network, 32, 3, padding='SAME', activation='relu')
network = max_pool_2d(network, 2, strides=2, padding='SAME')
network = conv_2d(network, 64, 3, padding='SAME', activation='relu')
network = max_pool_2d(network, 2, strides=2, padding='SAME')
network = conv_2d(network, 64, 3, padding='SAME', activation='relu')
network = max_pool_2d(network, 2, strides=2, padding='SAME')
network = conv_2d(network, 128, 3, padding='SAME', activation='relu')
network = flatten(network)
network = fully_connected(network, 3072, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 7, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
print('MODEL CREATED ....')
return network
def build_model(x, keep_prob, conv_ksize, conv_strides, pool_ksize,
pool_strides):
# First convolution & maxpooling
layer = conv_maxpool(x, 64, conv_ksize, conv_strides, pool_ksize,
pool_strides)
# Second convolution & maxpooling
layer = conv_maxpool(layer, 64, conv_ksize, conv_strides, pool_ksize,
pool_strides)
# Second convolution & maxpooling
# layer = conv_maxpool(layer, 1024, conv_ksize, conv_strides, pool_ksize, pool_strides)
# Flatten Layer
layer = flatten(layer)
# Fully connect layer
layer_output = fully_connected(layer,
1024,
activation='relu',
weights_init='truncated_normal',
bias_init='truncated_normal')
layer_output = dropout(layer_output, keep_prob)
layer_output = fully_connected(layer_output,
512,
activation='relu',
weights_init='truncated_normal',
bias_init='truncated_normal')
# layer_output = dropout(layer_output, keep_prob)
layer_output = fully_connected(layer_output,
10,
weights_init='truncated_normal',
bias_init='truncated_normal')
return layer_output
def tflearn_model():
network = input_data(shape=[None, 200, 66, 3], name='input')
network = batch_normalization(network, epsilon=0.001)
network = conv_2d(network, 24, 5, strides=2, activation='relu', padding='valid')
network = batch_normalization(network)
network = conv_2d(network, 36, 5, strides=2, activation='relu', padding='valid')
network = batch_normalization(network)
network = conv_2d(network, 48, 5, strides=2, activation='relu', padding='valid')
network = batch_normalization(network)
network = conv_2d(network, 64, 3, strides=1, activation='relu', padding='valid')
network = batch_normalization(network)
network = conv_2d(network, 64, 3, strides=1, activation='relu', padding='valid')
network = batch_normalization(network)
network = flatten(network)
network = fully_connected(network, 1164, activation='relu')
network = batch_normalization(network)
network = fully_connected(network, 100, activation='relu')
network = batch_normalization(network)
network = fully_connected(network, 50, activation='relu')
network = batch_normalization(network)
network = fully_connected(network, 10, activation='relu')
network = batch_normalization(network)
network = fully_connected(network, 2, activation='tanh')
network = regression(network, optimizer='adam', loss='mean_square', name='targets')
model = tflearn.DNN(network, checkpoint_path='nvidia_model', max_checkpoints=1,
tensorboard_verbose=0, tensorboard_dir='tflog')
return model
def create2dConvNetNeuralNetworkModel(input_size, output_size, learningRate):
# Specify the log directory
logdir = 'log/2d/' + datetime.now().strftime('%Y%m%d-%H%M%S')
convnet = input_data(shape=[None, input_size, input_size,1], name='input_currentState')
tflearn.init_graph(num_cores=1, gpu_memory_fraction=0.9)
convnet = conv_2d(convnet, nb_filter=16, filter_size=5, strides=1, padding='valid', activation='relu')
convnet = max_pool_2d(convnet, kernel_size=2, strides=2, padding='valid')
convnet = conv_2d(convnet, nb_filter=32, filter_size=3, strides=1, padding='valid', activation='relu')
convnet = max_pool_2d(convnet, kernel_size=2, strides=2, padding='valid')
convnet = flatten(convnet)
convnet = fully_connected(convnet, n_units=256, weights_init='truncated_normal', activation='relu')
convnet = dropout(convnet, 0.5)
convnet = fully_connected(convnet, n_units=128, weights_init='truncated_normal', activation='relu')
convnet = dropout(convnet, 0.5)
convnet = fully_connected(convnet, n_units=output_size, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=learningRate, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir=logdir)
return model
def classifier_forward(config,
incoming,
name=None,
reuse=False,
scope="classifier"):
with tf.variable_scope(scope, name, reuse=reuse):
network = incoming
network = relu(
batch_normalization(
conv_2d(network,
32,
5,
activation='relu',
regularizer="L2",
strides=2)))
network = relu(
batch_normalization(
conv_2d(network,
64,
5,
activation='relu',
regularizer="L2",
strides=2)))
network = flatten(network)
network = relu(batch_normalization(fully_connected(network, 1024)))
network = dropout(network, 0.5)
network = fully_connected(network, 10)
return network
def add_flatten_layer(self,
prev_layer_name=None,
exclude_from_path=True,
**kwargs):
prev_name = prev_layer_name or self._curr_layer_name
prev = self._layers[prev_name]['layer']
layer = {
"layer": core.flatten(prev, **kwargs),
"type": "Flatten",
"categories": ["hidden"]
}
return self._add_layer(layer, exclude_from_path)
def CNNModel(x, reuse=False):
conv_1 = conv_2d(x, 8, [32, 1], activation='relu', regularizer="L2", scope='conv_1', reuse=reuse)
avg_pool_1 = avg_pool_2d(conv_1, [1, 2])
output_layer_1 = local_response_normalization(avg_pool_1)
conv_2 = conv_2d(output_layer_1, 16, [1, 1], activation='relu', regularizer="L2", scope='conv_2', reuse=reuse)
avg_pool_2 = avg_pool_2d(conv_2, [1, 2])
output_layer_2 = local_response_normalization(avg_pool_2)
output_conv = flatten(output_layer_2)
return output_conv
def classifier_forward(config,
incoming,
name=None,
reuse=False,
scope="classifier"):
with tf.variable_scope(scope, name, reuse=reuse):
network = incoming
network = relu(conv_2d(network, 32, 5, strides=2))
network = relu(conv_2d(network, 64, 5, strides=2))
network = flatten(network)
network = relu(fully_connected(network, 1024))
network = dropout(network, 0.7)
network = fully_connected(network, 10)
return network
def NiN(input_layer, num_class):
network = conv_2d(input_layer, 192, 5, activation='relu')
network = conv_2d(network, 160, 1, activation='relu')
network = conv_2d(network, 96, 1, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 3, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 10, 1, activation='relu')
network = avg_pool_2d(network, 8)
network = flatten(network)
return network
def model_lenet5(data):
layer1_conv = conv_2d(data,
nb_filter=6,
filter_size=5,
strides=[1, 1, 1, 1],
activation='relu',
padding='SAME',
bias=True)
layer1_pool = avg_pool_2d(layer1_conv,
kernel_size=2,
strides=2,
padding='SAME')
layer2_conv = conv_2d(layer1_pool,
nb_filter=16,
filter_size=5,
strides=[1, 1, 1, 1],
activation='relu',
padding='VALID',
bias=True)
layer2_pool = avg_pool_2d(layer2_conv,
kernel_size=2,
strides=2,
padding='SAME')
flat_layer = flatten(layer2_pool)
layer3_fccd = fully_connected(flat_layer,
n_units=120,
activation='relu',
bias=True)
layer4_fccd = fully_connected(layer3_fccd,
n_units=84,
activation='relu',
bias=True)
#w = tf.Variable(tf.truncated_normal([84, 10], stddev=0.1))
#b = tf.Variable(tf.constant(1.0, shape = [10]))
#logits = tf.matmul(layer4_fccd, w) + b
logits = fully_connected(layer3_fccd,
n_units=10,
activation='relu',
bias=True)
return logits
def conv(classes, input_shape):
model = input_data(input_shape, name="input")
model = conv_2d(model, 32, (3, 3), activation='relu')
model = conv_2d(model, 64, (3, 3), activation='relu')
model = max_pool_2d(model, (2, 2))
model = dropout(model, 0.25)
model = flatten(model)
model = fully_connected(model, 128, activation='relu')
model = dropout(model, 0.5)
model = fully_connected(model, classes, activation='softmax')
model = regression(model,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='target')
# Training
model = tflearn.DNN(model, tensorboard_verbose=3)
return model
def retrain_sound_convnet(filepath):
data = load_sound_data()
trainX = data[2]
trainY = data[3]
testX = data[4]
testY = data[5]
## design the network
## input is a 89 x 89 nparray reshaped from the original 1 x 7921
## with the audio information
input_layer = input_data(shape=[None, 89, 89, 1])
## convolutional layer
conv_layer = conv_2d(input_layer,
nb_filter=32,
filter_size=2,
activation='sigmoid',
name='conv_layer_1')
## max pooling layer, window of 2x2
pool_layer = max_pool_2d(conv_layer, 2, name='pool_layer_2')
## dropout layer
dropout_layer = dropout(pool_layer, 0.25)
flat_layer = flatten(dropout_layer, name="flatten_layer")
## fully connected layer with 128
fc_layer_1 = fully_connected(flat_layer, 256, activation='relu', name='fc_layer_1')
## dropout layer
dropout_layer_1 = dropout(fc_layer_1, 0.25)
## fully connected with 3 layers, 0 is bee, 1 is cricket, 2 is ambient
fc_layer_2 = fully_connected(dropout_layer_1, 3, activation='softmax', name='fc_layer_2')
## network is trained with sgd, categorical cross entropy loss function, and eta = 0.01
network = regression(fc_layer_2, optimizer='sgd',
loss='categorical_crossentropy', learning_rate=0.01)
## turn the network into a model
model = tflearn.DNN(network)
model.load(filepath)
## now do the training on the network
NUM_EPOCHS = 150
BATCH_SIZE = 1
model.fit(trainX, trainY, n_epoch=NUM_EPOCHS,
shuffle=True,
validation_set=(testX, testY),
show_metric=True,
batch_size = BATCH_SIZE,
run_id='audio_convnet')
model.save(filepath)
def Convolution_NN(input_size, arg):
input_layer = input_data(shape=[None, input_size, input_size, arg],
name='input_layer')
conv1 = conv_2d(input_layer,
nb_filter=filter_size_1,
filter_size=6,
strides=1,
activation='relu',
regularizer='L2')
#conv1 = max_pool_2d(conv1,2)
conv2 = conv_2d(conv1,
nb_filter=filter_Size_2,
filter_size=5,
strides=2,
activation='relu',
regularizer='L2')
#conv2 = max_pool_2d(conv2,2)
conv3 = conv_2d(conv2,
nb_filter=filter_size_3,
filter_size=4,
strides=2,
activation='relu',
regularizer='L2')
full_layer1 = fully_connected(flatten(conv3),
fullyconnected_size,
activation='relu',
regularizer='L2')
full_layer1 = dropout(full_layer1, 0.75)
out_layer = fully_connected(full_layer1, 10, activation='softmax')
sgd = tflearn.SGD(learning_rate=0.1, lr_decay=0.096, decay_step=100)
top_k = tflearn.metrics.top_k(3)
network = regression(out_layer,
optimizer=sgd,
metric=top_k,
loss='categorical_crossentropy')
return tflearn.DNN(network,
tensorboard_dir='tf_CNN_board',
tensorboard_verbose=3)
def Net_in_Net1(network):
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 160, 1, activation='relu')
network = conv_2d(network, 96, 1, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 1.0)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 1.0)
network = conv_2d(network, 192, 3, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 10, 1, activation='relu')
network = avg_pool_2d(network, 8)
network = flatten(network)
network = fully_connected(network, output_dim, activation='softmax')
return network
def create_net():
"""
In this method che convolutional neural network is created.
Return:
---------
- model
"""
tf.reset_default_graph()
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name = 'input')
convnet = conv_2d(convnet, 32, 5, activation = 'relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation = 'relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 128, 5, activation = 'relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation = 'relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 32, 5, activation = 'relu')
convnet = max_pool_2d(convnet, 5)
convnet = flatten(convnet)
convnet = fully_connected(convnet, 1024, activation = 'relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation = 'softmax')
convnet = regression(convnet, optimizer = 'adam', learning_rate = LearningRate,
loss = 'categorical_crossentropy', name = 'targets')
model = tflearn.DNN(convnet, tensorboard_dir = 'log')
return model
def create_cnn_layers():
shape = [None, IMAGE_STD_HEIGHT, IMAGE_STD_WIDTH, RGB_COLOR_COUNT]
# input_layer = Input(name='input', shape=shape)
input_layer = input_data(name='input', shape=shape)
# h = Convolution2D(22, 5, 5, activation='relu', dim_ordering=dim_ordering)(input_layer)
h = conv_2d_specialized(input_layer, 22, [5, 5])
POOL_SIZE = [2, 2]
# h = MaxPooling2D(pool_size=POOL_SIZE)(h)
h = max_pool_2d(h, POOL_SIZE, padding='valid')
h = local_response_normalization(h)
# h = Convolution2D(44, 3, 3, activation='relu', dim_ordering=dim_ordering)(h)
h = conv_2d_specialized(h, 44, [3, 3])
# h = MaxPooling2D(pool_size=POOL_SIZE)(h)
h = max_pool_2d(h, POOL_SIZE, padding='valid')
h = local_response_normalization(h)
# h = Dropout(0.25)(h)
h = dropout(h, 1-0.25)
# last_cnn_layer = Flatten()(h)
last_cnn_layer = flatten(h)
return input_layer, last_cnn_layer
def build_network_in_network(self, network):
# network = input_data(shape=[None, 32, 32, 3])
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 160, 1, activation='relu')
network = conv_2d(network, 96, 1, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 3, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 2, 1, activation='relu')
network = avg_pool_2d(network, 8)
network = flatten(network)
network = regression(network, optimizer='adam',
loss='softmax_categorical_crossentropy',
learning_rate=0.001)
return network
def create_cnn_layers():
shape = [None, IMAGE_STD_HEIGHT, IMAGE_STD_WIDTH, RGB_COLOR_COUNT]
# input_layer = Input(name='input', shape=shape)
input_layer = input_data(name='input', shape=shape)
# h = Convolution2D(22, 5, 5, activation='relu', dim_ordering=dim_ordering)(input_layer)
h = conv_2d_specialized(input_layer, 22, [5, 5])
POOL_SIZE = [2, 2]
# h = MaxPooling2D(pool_size=POOL_SIZE)(h)
h = max_pool_2d(h, POOL_SIZE, padding='valid')
h = local_response_normalization(h)
# h = Convolution2D(44, 3, 3, activation='relu', dim_ordering=dim_ordering)(h)
h = conv_2d_specialized(h, 44, [3, 3])
# h = MaxPooling2D(pool_size=POOL_SIZE)(h)
h = max_pool_2d(h, POOL_SIZE, padding='valid')
h = local_response_normalization(h)
# h = Dropout(0.25)(h)
h = dropout(h, 1-0.25)
# last_cnn_layer = Flatten()(h)
last_cnn_layer = flatten(h)
return input_layer, last_cnn_layer
def Net_in_Net1(network, scale=False):
if scale is True:
network = scale(network)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 160, 1, activation='relu')
network = conv_2d(network, 96, 1, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 3, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 10, 1, activation='relu')
network = avg_pool_2d(network, 8)
network = flatten(network)
network = fully_connected(network, output_dim, activation='sigmoid')
return network
def le_net(IMG_PRE=img_pre, IMG_AUG=img_aug):
'''
Takes a custom Image Preprocessing and
Image Augmentation techniques.
'''
network = tflearn.input_data(shape=[None, 28, 28, 1],
data_preprocessing=IMG_PRE,
data_augmentation=IMG_AUG)
network = conv_2d(network, 32, (3, 3), activation='relu')
network = batch_normalization(network)
network = conv_2d(network, 32, (3, 3), activation='relu')
network = max_pool_2d(network, 2)
network = batch_normalization(network)
network = conv_2d(network, 64, (3, 3), activation='relu')
network = batch_normalization(network)
network = conv_2d(network, 64, (3, 3), activation='relu')
network = max_pool_2d(network, 2)
network = flatten(network)
network = batch_normalization(network)
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
network = batch_normalization(network)
network = fully_connected(network, 10, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
return network
batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None, name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(
conv_2d(tower_conv1, 288, 3, bias=False, strides=2, padding='VALID', activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(
batch_normalization(conv_2d(tower_conv2, 288, 3, bias=False, name='Conv2d_0b_3x3', activation=None)))
tower_conv2_2 = relu(batch_normalization(
conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID', activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
net = merge([tower_conv0_1, tower_conv1_1, tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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 = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = tflearn.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, shuffle=True,
show_metric=True, batch_size=32, snapshot_step=2000,
snapshot_epoch=False, run_id='inception_resnet_v2_17flowers')
def network(img_shape, name, LR):
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
#
# # Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_blur (sigma_max=3.0)
img_aug.add_random_flip_leftright()
img_aug.add_random_flip_updown()
img_aug.add_random_90degrees_rotation(rotations=[0, 2])
network = input_data(shape=img_shape, name=name, data_preprocessing=img_prep, data_augmentation=img_aug )
conv1a_3_3 = relu(batch_normalization(conv_2d(network, 32, 3, strides=2, bias=False, padding='VALID',activation=None,name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(batch_normalization(conv_2d(conv1a_3_3, 32, 3, bias=False, padding='VALID',activation=None, name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(batch_normalization(conv_2d(conv2a_3_3, 64, 3, bias=False, activation=None, name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3, 3, strides=2, padding='VALID', name='MaxPool_3a_3x3')
conv3b_1_1 = relu(batch_normalization(conv_2d(maxpool3a_3_3, 80, 1, bias=False, padding='VALID',activation=None, name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(batch_normalization(conv_2d(conv3b_1_1, 192, 3, bias=False, padding='VALID',activation=None, name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3, 3, strides=2, padding='VALID', name='MaxPool_5a_3x3')
tower_conv = relu(batch_normalization(conv_2d(maxpool5a_3_3, 96, 1, bias=False, activation=None, name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 48, 1, bias=False, activation=None, name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 64, 5, bias=False, activation=None, name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 64, 1, bias=False, activation=None, name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 96, 3, bias=False, activation=None, name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 96, 3, bias=False, activation=None,name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3, 3, strides=1, padding='same', name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(batch_normalization(conv_2d(tower_pool3_0, 64, 1, bias=False, activation=None,name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge([tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1], mode='concat', axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
tower_conv = relu(batch_normalization(conv_2d(net, 384, 3, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 3, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
# tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
# tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,3, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,1, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,3, bias=False, name='Conv2d_0b_3x3',activation=None)))
# tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 1, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
# tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID', name='MaxPool_1a_3x3')
net = merge([tower_conv0_1, tower_conv1_1,tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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 = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001, name='targets')
return network
def build_net(network,
X,
Y,
num_classes,
num_epochs,
checkpoint_path,
size_batch,
Xval=None,
Yval=None,
dec_step=100,
train=True):
tn = tflearn.initializations.truncated_normal(seed=100)
xav = tflearn.initializations.xavier(seed=100)
nor = tflearn.initializations.normal(seed=100)
network = conv_2d(network, 192, 5, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = conv_2d(network, 160, 1, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = conv_2d(network, 96, 1, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 5, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = conv_2d(network, 192, 1, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = conv_2d(network, 192, 1, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 3, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = conv_2d(network, 192, 1, weights_init=nor, regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = conv_2d(network,
num_classes,
1,
weights_init=nor,
regularizer='L2')
network = batch_normalization(network)
network = tflearn.activations.softplus(network)
network = avg_pool_2d(network, 9)
network = flatten(network)
adadelta = tflearn.optimizers.AdaDelta(learning_rate=0.01,
rho=0.95,
epsilon=1e-08)
network = regression(network,
optimizer=adadelta,
loss='softmax_categorical_crossentropy')
# Train
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path=checkpoint_path)
if train:
start_time = time.time()
if Xval is None or Yval is None:
model.fit(X,
Y,
n_epoch=num_epochs,
validation_set=0.0,
show_metric=True,
run_id='hsi_cnn_model',
shuffle=True,
batch_size=size_batch)
else:
model.fit(X,
Y,
n_epoch=num_epochs,
validation_set=(Xval, Yval),
show_metric=True,
run_id='hsi_cnn_model',
shuffle=True,
batch_size=size_batch)
print("\n\n-------------train time: %s seconds\n\n" %
(time.time() - start_time))
return model
def _model5():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
def block35(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 32, 3, bias=False, activation=None,name='Conv2d_0b_3x3')))
tower_conv2_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 48,3, bias=False, activation=None, name='Conv2d_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 64,3, bias=False, activation=None, name='Conv2d_0c_3x3')))
tower_mixed = merge([tower_conv, tower_conv1_1, tower_conv2_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block17(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv_1_0 = relu(batch_normalization(conv_2d(net, 128, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv_1_1 = relu(batch_normalization(conv_2d(tower_conv_1_0, 160,[1,7], bias=False, activation=None,name='Conv2d_0b_1x7')))
tower_conv_1_2 = relu(batch_normalization(conv_2d(tower_conv_1_1, 192, [7,1], bias=False, activation=None,name='Conv2d_0c_7x1')))
tower_mixed = merge([tower_conv,tower_conv_1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block8(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 224, [1,3], bias=False, activation=None, name='Conv2d_0b_1x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 256, [3,1], bias=False, name='Conv2d_0c_3x1')))
tower_mixed = merge([tower_conv,tower_conv1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
num_classes = len(Y[0])
dropout_keep_prob = 0.8
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
conv1a_3_3 = relu(batch_normalization(conv_2d(network, 32, 3, strides=2, bias=False, padding='VALID',activation=None,name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(batch_normalization(conv_2d(conv1a_3_3, 32, 3, bias=False, padding='VALID',activation=None, name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(batch_normalization(conv_2d(conv2a_3_3, 64, 3, bias=False, activation=None, name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3, 3, strides=2, padding='VALID', name='MaxPool_3a_3x3')
conv3b_1_1 = relu(batch_normalization(conv_2d(maxpool3a_3_3, 80, 1, bias=False, padding='VALID',activation=None, name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(batch_normalization(conv_2d(conv3b_1_1, 192, 3, bias=False, padding='VALID',activation=None, name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3, 3, strides=2, padding='VALID', name='MaxPool_5a_3x3')
tower_conv = relu(batch_normalization(conv_2d(maxpool5a_3_3, 96, 1, bias=False, activation=None, name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 48, 1, bias=False, activation=None, name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 64, 5, bias=False, activation=None, name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 64, 1, bias=False, activation=None, name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 96, 3, bias=False, activation=None, name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 96, 3, bias=False, activation=None,name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3, 3, strides=1, padding='same', name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(batch_normalization(conv_2d(tower_pool3_0, 64, 1, bias=False, activation=None,name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge([tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1], mode='concat', axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 3, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 3, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,3, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,3, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 1, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,1, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,1, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 1, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID', name='MaxPool_1a_3x3')
####
net = merge([tower_conv0_1, tower_conv1_1,tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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 = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = tflearn.DNN(network, checkpoint_path='inception_resnet_v2',
max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir="./tflearn_logs/")
model.fit(X, Y, n_epoch=epochNum, validation_set=(xTest, yTest), shuffle=True,
show_metric=True, batch_size=batchNum, snapshot_step=2000,
snapshot_epoch=False, run_id='inception_resnet_v2_oxflowers17')
if modelStore: model.save(_id + '-model.tflearn')
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,3, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,3, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
net = merge([tower_conv0_1, tower_conv1_1,tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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 = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = tflearn.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, shuffle=True,
show_metric=True, batch_size=32, snapshot_step=2000,
snapshot_epoch=False, run_id='inception_resnet_v2_17flowers')
def _model5():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
def block35(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 32, 3, bias=False, activation=None,name='Conv2d_0b_3x3')))
tower_conv2_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 48,3, bias=False, activation=None, name='Conv2d_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 64,3, bias=False, activation=None, name='Conv2d_0c_3x3')))
tower_mixed = merge([tower_conv, tower_conv1_1, tower_conv2_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block17(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv_1_0 = relu(batch_normalization(conv_2d(net, 128, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv_1_1 = relu(batch_normalization(conv_2d(tower_conv_1_0, 160,[1,7], bias=False, activation=None,name='Conv2d_0b_1x7')))
tower_conv_1_2 = relu(batch_normalization(conv_2d(tower_conv_1_1, 192, [7,1], bias=False, activation=None,name='Conv2d_0c_7x1')))
tower_mixed = merge([tower_conv,tower_conv_1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block8(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 224, [1,3], bias=False, activation=None, name='Conv2d_0b_1x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 256, [3,1], bias=False, name='Conv2d_0c_3x1')))
tower_mixed = merge([tower_conv,tower_conv1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
num_classes = len(yTest[0])
dropout_keep_prob = 0.8
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
conv1a_3_3 = relu(batch_normalization(conv_2d(network, 32, 3, strides=2, bias=False, padding='VALID',activation=None,name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(batch_normalization(conv_2d(conv1a_3_3, 32, 3, bias=False, padding='VALID',activation=None, name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(batch_normalization(conv_2d(conv2a_3_3, 64, 3, bias=False, activation=None, name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3, 3, strides=2, padding='VALID', name='MaxPool_3a_3x3')
conv3b_1_1 = relu(batch_normalization(conv_2d(maxpool3a_3_3, 80, 1, bias=False, padding='VALID',activation=None, name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(batch_normalization(conv_2d(conv3b_1_1, 192, 3, bias=False, padding='VALID',activation=None, name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3, 3, strides=2, padding='VALID', name='MaxPool_5a_3x3')
tower_conv = relu(batch_normalization(conv_2d(maxpool5a_3_3, 96, 1, bias=False, activation=None, name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 48, 1, bias=False, activation=None, name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 64, 5, bias=False, activation=None, name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 64, 1, bias=False, activation=None, name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 96, 3, bias=False, activation=None, name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 96, 3, bias=False, activation=None,name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3, 3, strides=1, padding='same', name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(batch_normalization(conv_2d(tower_pool3_0, 64, 1, bias=False, activation=None,name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge([tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1], mode='concat', axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 3, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 3, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,3, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,3, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 1, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,1, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,1, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 1, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID', name='MaxPool_1a_3x3')
####
net = merge([tower_conv0_1, tower_conv1_1,tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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 = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = tflearn.DNN(network, checkpoint_path='inception_resnet_v2',
max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir="./tflearn_logs/")
model.load(_path)
pred = model.predict(xTest)
df = pd.DataFrame(pred)
df.to_csv(_path + ".csv")
newList = pred.copy()
newList = convert2(newList)
if _CSV: makeCSV(newList)
pred = convert2(pred)
pred = convert3(pred)
yTest = convert3(yTest)
print(metrics.confusion_matrix(yTest, pred))
print(metrics.classification_report(yTest, pred))
print('Accuracy', accuracy_score(yTest, pred))
print()
if _wrFile: writeTest(pred)
(X, Y), (X_test, Y_test) = cifar10.load_data()
X, Y = shuffle(X, Y)
Y = to_categorical(Y, 10)
Y_test = to_categorical(Y_test, 10)
# Building 'Network In Network'
network = input_data(shape=[None, 32, 32, 3])
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 160, 1, activation='relu')
network = conv_2d(network, 96, 1, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 3, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 10, 1, activation='relu')
network = avg_pool_2d(network, 8)
network = flatten(network)
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Training
model = tflearn.DNN(network)
model.fit(X, Y, n_epoch=50, shuffle=True, validation_set=(X_test, Y_test),
show_metric=True, batch_size=128, run_id='cifar10_net_in_net')
}
# Build CNN
input_data = input_data(shape=[None, 32, 32, 3], data_augmentation=img_aug)
conv1 = conv_2d(input_data, 64, params['conv_filter'], activation='relu', regularizer='L2')
pool1 = max_pool_2d(conv1, params['pool_width'], params['pool_stride'])
lrn1 = local_response_normalization(pool1)
conv2 = conv_2d(lrn1, 64, params['conv_filter'], activation='relu', regularizer='L2')
pool2 = max_pool_2d(conv2, params['pool_width'], params['pool_stride'])
lrn2 = local_response_normalization(pool2)
conv3 = conv_2d(lrn2, 128, params['conv_filter'], activation='relu', regularizer='L2')
pool3 = max_pool_2d(conv3, params['pool_width'], params['pool_stride'])
lrn3 = local_response_normalization(pool3)
flat = flatten(lrn3)
fully1 = fully_connected(lrn3, 384, activation='relu')
drop1 = dropout(fully1, 0.5)
fully2 = fully_connected(drop1, 384/2, activation='relu')
drop2 = dropout(fully2, 0.5)
fully3 = fully_connected(drop2, 10, activation='softmax')
network = regression(fully3, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001, name='Target')
# Define model
model = tflearn.DNN(network, tensorboard_verbose=0, tensorboard_dir='../log/')
# Predict
model.load('../log/model_4/'+params['id']+'.tflearn')
conv_1 = relu(conv_2d(network, 64, 7, strides=2, bias=True, padding=padding, activation=None, name='Conv2d_1'))
maxpool_1 = batch_normalization(max_pool_2d(conv_1, 3, strides=2, padding=padding, name='MaxPool_1'))
#LRN_1 = local_response_normalization(maxpool_1, name='LRN_1')
# FeatEX-1
conv_2a = relu(conv_2d(maxpool_1, 96, 1, strides=1, padding=padding, name='Conv_2a_FX1'))
maxpool_2a = max_pool_2d(maxpool_1, 3, strides=1, padding=padding, name='MaxPool_2a_FX1')
conv_2b = relu(conv_2d(conv_2a, 208, 3, strides=1, padding=padding, name='Conv_2b_FX1'))
conv_2c = relu(conv_2d(maxpool_2a, 64, 1, strides=1, padding=padding, name='Conv_2c_FX1'))
FX1_out = merge([conv_2b, conv_2c], mode='concat', axis=3, name='FX1_out')
# FeatEX-2
conv_3a = relu(conv_2d(FX1_out, 96, 1, strides=1, padding=padding, name='Conv_3a_FX2'))
maxpool_3a = max_pool_2d(FX1_out, 3, strides=1, padding=padding, name='MaxPool_3a_FX2')
conv_3b = relu(conv_2d(conv_3a, 208, 3, strides=1, padding=padding, name='Conv_3b_FX2'))
conv_3c = relu(conv_2d(maxpool_3a, 64, 1, strides=1, padding=padding, name='Conv_3c_FX2'))
FX2_out = merge([conv_3b, conv_3c], mode='concat', axis=3, name='FX2_out')
net = flatten(FX2_out)
if do:
net = dropout(net, dropout_keep_prob)
loss = fully_connected(net, num_classes,activation='softmax')
# Compile the model and define the hyperparameters
network = tflearn.regression(loss, optimizer='Adam',
loss='categorical_crossentropy',
learning_rate=LR)
# Final definition of model checkpoints and other configurations
model = tflearn.DNN(network, checkpoint_path='../DeXpression/DeXpression_checkpoints',
max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir="./tflearn_logs/")
# Save the model
#model.save('../DeXpression/DeXpression_checkpoints/' + RUNID + '.model')
network = input_data(shape=[None, 32, 32, 3])
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 160, 1, activation='relu')
network = conv_2d(network, 96, 1, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 5, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = avg_pool_2d(network, 3, strides=2)
network = dropout(network, 0.5)
network = conv_2d(network, 192, 3, activation='relu')
network = conv_2d(network, 192, 1, activation='relu')
network = conv_2d(network, 10, 1, activation='relu')
network = avg_pool_2d(network, 8)
network = flatten(network)
network = regression(network,
optimizer='adam',
loss='softmax_categorical_crossentropy',
learning_rate=0.001)
# training
model = tflearn.DNN(network)
model.fit(X,
Y,
n_epoch=50,
shuffle=True,
validation_set=(X_test, Y_test),
show_metric=True,
batch_size=128,
run_id='cifar10_net_in_net')
def inception_v2(width, height, learning_rate):
num_classes = 17
dropout_keep_prob = 0.8
network = input_data(shape=[None, width, height, 3])
conv1a_3_3 = relu(
batch_normalization(
conv_2d(network,
32,
3,
strides=2,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(
batch_normalization(
conv_2d(conv1a_3_3,
32,
3,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(
batch_normalization(
conv_2d(conv2a_3_3,
64,
3,
bias=False,
activation=None,
name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3,
3,
strides=2,
padding='VALID',
name='MaxPool_3a_3x3')
conv3b_1_1 = relu(
batch_normalization(
conv_2d(maxpool3a_3_3,
80,
1,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(
batch_normalization(
conv_2d(conv3b_1_1,
192,
3,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3,
3,
strides=2,
padding='VALID',
name='MaxPool_5a_3x3')
tower_conv = relu(
batch_normalization(
conv_2d(maxpool5a_3_3,
96,
1,
bias=False,
activation=None,
name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(
batch_normalization(
conv_2d(maxpool5a_3_3,
48,
1,
bias=False,
activation=None,
name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1_0,
64,
5,
bias=False,
activation=None,
name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(
batch_normalization(
conv_2d(maxpool5a_3_3,
64,
1,
bias=False,
activation=None,
name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(
batch_normalization(
conv_2d(tower_conv2_0,
96,
3,
bias=False,
activation=None,
name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(
batch_normalization(
conv_2d(tower_conv2_1,
96,
3,
bias=False,
activation=None,
name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3,
3,
strides=1,
padding='same',
name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(
batch_normalization(
conv_2d(tower_pool3_0,
64,
1,
bias=False,
activation=None,
name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge(
[tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1],
mode='concat',
axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
tower_conv = relu(
batch_normalization(
conv_2d(net,
384,
3,
bias=False,
strides=2,
activation=None,
padding='VALID',
name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
activation=None,
name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1_0,
256,
3,
bias=False,
activation=None,
name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(
batch_normalization(
conv_2d(tower_conv1_1,
384,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net,
3,
strides=2,
padding='VALID',
name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(
batch_normalization(
conv_2d(tower_conv,
384,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='Conv2d_0a_1x1')))
tower_conv1 = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1,
288,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='COnv2d_1a_3x3')))
tower_conv2 = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(
batch_normalization(
conv_2d(tower_conv2,
288,
3,
bias=False,
name='Conv2d_0b_3x3',
activation=None)))
tower_conv2_2 = relu(
batch_normalization(
conv_2d(tower_conv2_1,
320,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net,
3,
strides=2,
padding='VALID',
name='MaxPool_1a_3x3')
net = merge([tower_conv0_1, tower_conv1_1, tower_conv2_2, tower_pool],
mode='concat',
axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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 = tflearn.regression(loss,
optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=learning_rate)
#learning_rate=0.0001)
model = tflearn.DNN(network,
checkpoint_path='inception_resnet_v2',
max_checkpoints=1,
tensorboard_verbose=2,
tensorboard_dir="./tflearn_logs/")
return model
def imageFetch(self):
image_path = self.path
IMG_SIZE1 = 175
IMG_SIZE2 = 150
test_data = []
image = cv2.imread(image_path, cv2.IMREAD_GRAYSCALE)
test_image = cv2.resize(image, (IMG_SIZE1, IMG_SIZE2))
test_data.append([np.array(test_image)])
LR = 0.0001
MODEL_NAME = 'ECR-{}-{}.model'.format(LR, '2conv-basic')
convnet = input_data(shape=[None, IMG_SIZE1, IMG_SIZE2, 1],
name='input')
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = dropout(convnet, 0.3)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = dropout(convnet, 0.3)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = dropout(convnet, 0.3)
convnet = conv_2d(convnet, 128, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = flatten(convnet)
convnet = fully_connected(convnet, 256, activation='relu')
convnet = dropout(convnet, 0.3)
convnet = fully_connected(convnet, 512, activation='relu')
convnet = dropout(convnet, 0.3)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
learning_rate=LR,
loss='binary_crossentropy',
name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('Explicit Content Sensor Loaded !')
for num, data in enumerate(test_data[:]):
test_img = data[0]
test_img_reshaped = test_img.reshape(IMG_SIZE1, IMG_SIZE2, 1)
model_out = model.predict([test_img_reshaped])[0]
if np.argmax(model_out) == 1:
str_label = 1
# Non-Explicit Content
else:
str_label = 0
# Explicit Content
final_image = cv2.imread(image_path)
cv2.namedWindow('Image Viewer', cv2.WINDOW_NORMAL)
if str_label == 0:
final_image = cv2.blur(final_image, (200, 200))
cv2.imshow("Image Viewer", final_image)
k = cv2.waitKey(0) & 0xFF
if k == 27:
cv2.destroyAllWindows()
def ImageNetInceptionV2(outnode,
model_name,
target,
opt,
learn_r,
epch,
dropout_keep_rate,
save_model=False):
def block35(net, scale=1.0, activation="relu"):
tower_conv = relu(
batch_normalization(
conv_2d(net,
32,
1,
bias=False,
activation=None,
name='Conv2d_1x1')))
tower_conv1_0 = relu(
batch_normalization(
conv_2d(net,
32,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1_0,
32,
3,
bias=False,
activation=None,
name='Conv2d_0b_3x3')))
tower_conv2_0 = relu(
batch_normalization(
conv_2d(net,
32,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(
batch_normalization(
conv_2d(tower_conv2_0,
48,
3,
bias=False,
activation=None,
name='Conv2d_0b_3x3')))
tower_conv2_2 = relu(
batch_normalization(
conv_2d(tower_conv2_1,
64,
3,
bias=False,
activation=None,
name='Conv2d_0c_3x3')))
tower_mixed = merge([tower_conv, tower_conv1_1, tower_conv2_2],
mode='concat',
axis=3)
tower_out = relu(
batch_normalization(
conv_2d(tower_mixed,
net.get_shape()[3],
1,
bias=False,
activation=None,
name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block17(net, scale=1.0, activation="relu"):
tower_conv = relu(
batch_normalization(
conv_2d(net,
192,
1,
bias=False,
activation=None,
name='Conv2d_1x1')))
tower_conv_1_0 = relu(
batch_normalization(
conv_2d(net,
128,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv_1_1 = relu(
batch_normalization(
conv_2d(tower_conv_1_0,
160, [1, 7],
bias=False,
activation=None,
name='Conv2d_0b_1x7')))
tower_conv_1_2 = relu(
batch_normalization(
conv_2d(tower_conv_1_1,
192, [7, 1],
bias=False,
activation=None,
name='Conv2d_0c_7x1')))
tower_mixed = merge([tower_conv, tower_conv_1_2],
mode='concat',
axis=3)
tower_out = relu(
batch_normalization(
conv_2d(tower_mixed,
net.get_shape()[3],
1,
bias=False,
activation=None,
name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block8(net, scale=1.0, activation="relu"):
tower_conv = relu(
batch_normalization(
conv_2d(net,
192,
1,
bias=False,
activation=None,
name='Conv2d_1x1')))
tower_conv1_0 = relu(
batch_normalization(
conv_2d(net,
192,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1_0,
224, [1, 3],
bias=False,
activation=None,
name='Conv2d_0b_1x3')))
tower_conv1_2 = relu(
batch_normalization(
conv_2d(tower_conv1_1,
256, [3, 1],
bias=False,
name='Conv2d_0c_3x1')))
tower_mixed = merge([tower_conv, tower_conv1_2], mode='concat', axis=3)
tower_out = relu(
batch_normalization(
conv_2d(tower_mixed,
net.get_shape()[3],
1,
bias=False,
activation=None,
name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
# default = 0.8
dropout_keep_prob = dropout_keep_rate
network = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
conv1a_3_3 = relu(
batch_normalization(
conv_2d(network,
32,
3,
strides=2,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(
batch_normalization(
conv_2d(conv1a_3_3,
32,
3,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(
batch_normalization(
conv_2d(conv2a_3_3,
64,
3,
bias=False,
activation=None,
name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3,
3,
strides=2,
padding='VALID',
name='MaxPool_3a_3x3')
conv3b_1_1 = relu(
batch_normalization(
conv_2d(maxpool3a_3_3,
80,
1,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(
batch_normalization(
conv_2d(conv3b_1_1,
192,
3,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3,
3,
strides=2,
padding='VALID',
name='MaxPool_5a_3x3')
tower_conv = relu(
batch_normalization(
conv_2d(maxpool5a_3_3,
96,
1,
bias=False,
activation=None,
name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(
batch_normalization(
conv_2d(maxpool5a_3_3,
48,
1,
bias=False,
activation=None,
name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1_0,
64,
5,
bias=False,
activation=None,
name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(
batch_normalization(
conv_2d(maxpool5a_3_3,
64,
1,
bias=False,
activation=None,
name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(
batch_normalization(
conv_2d(tower_conv2_0,
96,
3,
bias=False,
activation=None,
name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(
batch_normalization(
conv_2d(tower_conv2_1,
96,
3,
bias=False,
activation=None,
name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3,
3,
strides=1,
padding='same',
name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(
batch_normalization(
conv_2d(tower_pool3_0,
64,
1,
bias=False,
activation=None,
name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge(
[tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1],
mode='concat',
axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
tower_conv = relu(
batch_normalization(
conv_2d(net,
384,
3,
bias=False,
strides=2,
activation=None,
padding='VALID',
name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
activation=None,
name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1_0,
256,
3,
bias=False,
activation=None,
name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(
batch_normalization(
conv_2d(tower_conv1_1,
384,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net,
3,
strides=2,
padding='VALID',
name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(
batch_normalization(
conv_2d(tower_conv,
384,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='Conv2d_0a_1x1')))
tower_conv1 = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
padding='VALID',
activation=None,
name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(
batch_normalization(
conv_2d(tower_conv1,
288,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='COnv2d_1a_3x3')))
tower_conv2 = relu(
batch_normalization(
conv_2d(net,
256,
1,
bias=False,
activation=None,
name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(
batch_normalization(
conv_2d(tower_conv2,
288,
3,
bias=False,
name='Conv2d_0b_3x3',
activation=None)))
tower_conv2_2 = relu(
batch_normalization(
conv_2d(tower_conv2_1,
320,
3,
bias=False,
strides=2,
padding='VALID',
activation=None,
name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net,
3,
strides=2,
padding='VALID',
name='MaxPool_1a_3x3')
net = merge([tower_conv0_1, tower_conv1_1, tower_conv2_2, tower_pool],
mode='concat',
axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
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, outnode, activation='softmax')
str_model_name = "{}_{}_{}_{}_{}_{}".format(model_name, target, opt,
learn_r, epch,
dropout_keep_rate)
network = tflearn.regression(loss,
optimizer=opt,
loss='categorical_crossentropy',
learning_rate=learn_r,
name='targets')
model = None
if save_model:
model = tflearn.DNN(
network,
checkpoint_path='../tflearnModels/{}'.format(str_model_name),
best_checkpoint_path='../tflearnModels/bestModels/best_{}'.format(
str_model_name),
max_checkpoints=1,
tensorboard_verbose=0,
tensorboard_dir="../tflearnLogs/{}/".format(str_model_name))
else:
model = tflearn.DNN(network)
return model
def videoFetch(self,thread_id):
path = self.path
img_width = 175
img_height = 150
testing_data = []
start_time = time.time()
cap = cv2.VideoCapture(path)
frame_count = cap.get(cv2.CAP_PROP_FRAME_COUNT) - 1
fragment_size = frame_count/8
init_frame = math.floor(fragment_size*thread_id)
end_frame = math.floor(fragment_size*(thread_id+1)-1)
count = init_frame
cap.set(1,init_frame)
while cap.isOpened():
ret, frame = cap.read()
if(ret):
img = cv2.resize(frame, (img_width,img_height))
img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img_num = "%#05d" % (count+1)
testing_data.append([np.array(img),img_num])
count = count+1
if (count == end_frame):
end_time = time.time()
cap.release()
print ("{} Done extracting frames.\n{} frames found".format(thread_id,end_frame-init_frame))
print ("It took %d seconds forconversion." % (end_time-start_time))
break
# np.save('/home/ghost/Desktop/ecc/test_data_{}.npy'.format(thread_id), testing_data)
LR = 0.0001
MODEL_NAME = 'ECR-{}-{}.model'.format(LR, '2conv-basic')
tf.reset_default_graph()
convnet = input_data(shape=[None, IMG_SIZE1, IMG_SIZE2, 1], name='input')
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = dropout(convnet, 0.2)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = flatten(convnet)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.4)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='binary_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load('../'+MODEL_NAME)
print('model loaded!')
