def google_graph(X):
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_crop([64, 64], padding=4)
network = input_data(shape=[None, 64, 64, 3], data_preprocessing=img_prep, data_augmentation=img_aug)
conv1_7_7 = conv_2d(network, 64, 7, strides=2, activation='relu', name='conv1_7_7_s2')
pool1_3_3 = max_pool_2d(conv1_7_7, 3, strides=2)
pool1_3_3 = local_response_normalization(pool1_3_3)
conv2_3_3_reduce = conv_2d(pool1_3_3, 64, 1, activation='relu', name='conv2_3_3_reduce')
conv2_3_3 = conv_2d(conv2_3_3_reduce, 192, 3, activation='relu', name='conv2_3_3')
conv2_3_3 = local_response_normalization(conv2_3_3)
pool2_3_3 = max_pool_2d(conv2_3_3, kernel_size=3, strides=2, name='pool2_3_3_s2')
inception_3a_1_1 = conv_2d(pool2_3_3, 64, 1, activation='relu', name='inception_3a_1_1')
inception_3a_3_3_reduce = conv_2d(pool2_3_3, 96, 1, activation='relu', name='inception_3a_3_3_reduce')
inception_3a_3_3 = conv_2d(inception_3a_3_3_reduce, 128, filter_size=3, activation='relu', name='inception_3a_3_3')
inception_3a_5_5_reduce = conv_2d(pool2_3_3, 16, filter_size=1, activation='relu', name='inception_3a_5_5_reduce')
inception_3a_5_5 = conv_2d(inception_3a_5_5_reduce, 32, filter_size=5, activation='relu', name='inception_3a_5_5')
inception_3a_pool = max_pool_2d(pool2_3_3, kernel_size=3, strides=1, )
inception_3a_pool_1_1 = conv_2d(inception_3a_pool, 32, filter_size=1, activation='relu',
name='inception_3a_pool_1_1')
# merge the inception_3a__
inception_3a_output = merge([inception_3a_1_1, inception_3a_3_3, inception_3a_5_5, inception_3a_pool_1_1],
mode='concat', axis=3)
inception_3b_1_1 = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu', name='inception_3b_1_1')
inception_3b_3_3_reduce = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu',
name='inception_3b_3_3_reduce')
inception_3b_3_3 = conv_2d(inception_3b_3_3_reduce, 192, filter_size=3, activation='relu', name='inception_3b_3_3')
inception_3b_5_5_reduce = conv_2d(inception_3a_output, 32, filter_size=1, activation='relu',
name='inception_3b_5_5_reduce')
inception_3b_5_5 = conv_2d(inception_3b_5_5_reduce, 96, filter_size=5, name='inception_3b_5_5')
inception_3b_pool = max_pool_2d(inception_3a_output, kernel_size=3, strides=1, name='inception_3b_pool')
inception_3b_pool_1_1 = conv_2d(inception_3b_pool, 64, filter_size=1, activation='relu',
name='inception_3b_pool_1_1')
# merge the inception_3b_*
inception_3b_output = merge([inception_3b_1_1, inception_3b_3_3, inception_3b_5_5, inception_3b_pool_1_1],
mode='concat', axis=3, name='inception_3b_output')
pool3_3_3 = max_pool_2d(inception_3b_output, kernel_size=3, strides=2, name='pool3_3_3')
inception_4a_1_1 = conv_2d(pool3_3_3, 192, filter_size=1, activation='relu', name='inception_4a_1_1')
inception_4a_3_3_reduce = conv_2d(pool3_3_3, 96, filter_size=1, activation='relu', name='inception_4a_3_3_reduce')
inception_4a_3_3 = conv_2d(inception_4a_3_3_reduce, 208, filter_size=3, activation='relu', name='inception_4a_3_3')
inception_4a_5_5_reduce = conv_2d(pool3_3_3, 16, filter_size=1, activation='relu', name='inception_4a_5_5_reduce')
inception_4a_5_5 = conv_2d(inception_4a_5_5_reduce, 48, filter_size=5, activation='relu', name='inception_4a_5_5')
inception_4a_pool = max_pool_2d(pool3_3_3, kernel_size=3, strides=1, name='inception_4a_pool')
inception_4a_pool_1_1 = conv_2d(inception_4a_pool, 64, filter_size=1, activation='relu',
name='inception_4a_pool_1_1')
inception_4a_output = merge([inception_4a_1_1, inception_4a_3_3, inception_4a_5_5, inception_4a_pool_1_1],
mode='concat', axis=3, name='inception_4a_output')
inception_4b_1_1 = conv_2d(inception_4a_output, 160, filter_size=1, activation='relu', name='inception_4a_1_1')
inception_4b_3_3_reduce = conv_2d(inception_4a_output, 112, filter_size=1, activation='relu',
name='inception_4b_3_3_reduce')
inception_4b_3_3 = conv_2d(inception_4b_3_3_reduce, 224, filter_size=3, activation='relu', name='inception_4b_3_3')
inception_4b_5_5_reduce = conv_2d(inception_4a_output, 24, filter_size=1, activation='relu',
name='inception_4b_5_5_reduce')
inception_4b_5_5 = conv_2d(inception_4b_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4b_5_5')
inception_4b_pool = max_pool_2d(inception_4a_output, kernel_size=3, strides=1, name='inception_4b_pool')
inception_4b_pool_1_1 = conv_2d(inception_4b_pool, 64, filter_size=1, activation='relu',
name='inception_4b_pool_1_1')
inception_4b_output = merge([inception_4b_1_1, inception_4b_3_3, inception_4b_5_5, inception_4b_pool_1_1],
mode='concat', axis=3, name='inception_4b_output')
inception_4c_1_1 = conv_2d(inception_4b_output, 128, filter_size=1, activation='relu', name='inception_4c_1_1')
inception_4c_3_3_reduce = conv_2d(inception_4b_output, 128, filter_size=1, activation='relu',
name='inception_4c_3_3_reduce')
inception_4c_3_3 = conv_2d(inception_4c_3_3_reduce, 256, filter_size=3, activation='relu', name='inception_4c_3_3')
inception_4c_5_5_reduce = conv_2d(inception_4b_output, 24, filter_size=1, activation='relu',
name='inception_4c_5_5_reduce')
inception_4c_5_5 = conv_2d(inception_4c_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4c_5_5')
inception_4c_pool = max_pool_2d(inception_4b_output, kernel_size=3, strides=1)
inception_4c_pool_1_1 = conv_2d(inception_4c_pool, 64, filter_size=1, activation='relu',
name='inception_4c_pool_1_1')
inception_4c_output = merge([inception_4c_1_1, inception_4c_3_3, inception_4c_5_5, inception_4c_pool_1_1],
mode='concat', axis=3, name='inception_4c_output')
inception_4d_1_1 = conv_2d(inception_4c_output, 112, filter_size=1, activation='relu', name='inception_4d_1_1')
inception_4d_3_3_reduce = conv_2d(inception_4c_output, 144, filter_size=1, activation='relu',
name='inception_4d_3_3_reduce')
inception_4d_3_3 = conv_2d(inception_4d_3_3_reduce, 288, filter_size=3, activation='relu', name='inception_4d_3_3')
inception_4d_5_5_reduce = conv_2d(inception_4c_output, 32, filter_size=1, activation='relu',
name='inception_4d_5_5_reduce')
inception_4d_5_5 = conv_2d(inception_4d_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4d_5_5')
inception_4d_pool = max_pool_2d(inception_4c_output, kernel_size=3, strides=1, name='inception_4d_pool')
inception_4d_pool_1_1 = conv_2d(inception_4d_pool, 64, filter_size=1, activation='relu',
name='inception_4d_pool_1_1')
inception_4d_output = merge([inception_4d_1_1, inception_4d_3_3, inception_4d_5_5, inception_4d_pool_1_1],
mode='concat', axis=3, name='inception_4d_output')
inception_4e_1_1 = conv_2d(inception_4d_output, 256, filter_size=1, activation='relu', name='inception_4e_1_1')
inception_4e_3_3_reduce = conv_2d(inception_4d_output, 160, filter_size=1, activation='relu',
name='inception_4e_3_3_reduce')
inception_4e_3_3 = conv_2d(inception_4e_3_3_reduce, 320, filter_size=3, activation='relu', name='inception_4e_3_3')
inception_4e_5_5_reduce = conv_2d(inception_4d_output, 32, filter_size=1, activation='relu',
name='inception_4e_5_5_reduce')
inception_4e_5_5 = conv_2d(inception_4e_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_4e_5_5')
inception_4e_pool = max_pool_2d(inception_4d_output, kernel_size=3, strides=1, name='inception_4e_pool')
inception_4e_pool_1_1 = conv_2d(inception_4e_pool, 128, filter_size=1, activation='relu',
name='inception_4e_pool_1_1')
inception_4e_output = merge([inception_4e_1_1, inception_4e_3_3, inception_4e_5_5, inception_4e_pool_1_1], axis=3,
mode='concat')
pool4_3_3 = max_pool_2d(inception_4e_output, kernel_size=3, strides=2, name='pool_3_3')
inception_5a_1_1 = conv_2d(pool4_3_3, 256, filter_size=1, activation='relu', name='inception_5a_1_1')
inception_5a_3_3_reduce = conv_2d(pool4_3_3, 160, filter_size=1, activation='relu', name='inception_5a_3_3_reduce')
inception_5a_3_3 = conv_2d(inception_5a_3_3_reduce, 320, filter_size=3, activation='relu', name='inception_5a_3_3')
inception_5a_5_5_reduce = conv_2d(pool4_3_3, 32, filter_size=1, activation='relu', name='inception_5a_5_5_reduce')
inception_5a_5_5 = conv_2d(inception_5a_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_5a_5_5')
inception_5a_pool = max_pool_2d(pool4_3_3, kernel_size=3, strides=1, name='inception_5a_pool')
inception_5a_pool_1_1 = conv_2d(inception_5a_pool, 128, filter_size=1, activation='relu',
name='inception_5a_pool_1_1')
inception_5a_output = merge([inception_5a_1_1, inception_5a_3_3, inception_5a_5_5, inception_5a_pool_1_1], axis=3,
mode='concat')
inception_5b_1_1 = conv_2d(inception_5a_output, 384, filter_size=1, activation='relu', name='inception_5b_1_1')
inception_5b_3_3_reduce = conv_2d(inception_5a_output, 192, filter_size=1, activation='relu',
name='inception_5b_3_3_reduce')
inception_5b_3_3 = conv_2d(inception_5b_3_3_reduce, 384, filter_size=3, activation='relu', name='inception_5b_3_3')
inception_5b_5_5_reduce = conv_2d(inception_5a_output, 48, filter_size=1, activation='relu',
name='inception_5b_5_5_reduce')
inception_5b_5_5 = conv_2d(inception_5b_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_5b_5_5')
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)
network = fully_connected(pool5_7_7, 2, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0005)
google_model = tflearn.DNN(network)
google_model.load('model\\google\\jun_glnet_cat_dog_final.tflearn')
google_result = google_model.predict(X)
return google_result
from tflearn.data_augmentation import ImageAugmentation
import pickle
#Loading dataset
X_train, Y_train, X_test, Y_test = pickle.load(open("full_dataset.pkl", "rb"))
#Shuffle dataset
X_train, Y_train = shuffle(X_train, Y_train)
#Normalise dataset
preprocessed_img = ImagePreprocessing()
preprocessed_img.add_featurewise_zero_center()
preprocessed_img.add_featurewise_stdnorm()
#Augmenting dataset
augmented_image = ImageAugmentation()
augmented_image.add_random_flip_leftright()
augmented_image.add_random_rotation(max_angle=25.)
augmented_image.add_random_blur(sigma_max=3.)
#Network
neural_net = input_data(shape=[None, 32, 32, 3],
data_preprocessing=preprocessed_img,
data_augmentation=augmented_image)
neural_net = conv_2d(neural_net, 32, 3, activation='relu')
neural_net = max_pool_2d(neural_net, 2)
neural_net = conv_2d(neural_net, 64, 3, activation='relu')
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 color():
###################################
### Import picture files
###################################
files_path = "./img_align_celeba/"
glasses_files_path = os.path.join(files_path, '*.jpg')
glasses_files = sorted(glob(glasses_files_path))
n_files = len(glasses_files)
#print(n_files)
#size_image1 =178
#size_image2=218
size_image1=27
size_image2=33
allX = np.zeros((n_files, size_image1, size_image2, 3), dtype='float32')
ally = np.zeros(n_files)
count = 0
for f in glasses_files:
try:
img = io.imread(f)
new_img = skimage.transform.resize(img, (27, 33, 3))
allX[count] = np.array(new_img)
ally[count] = 0
count += 1
except:
continue
attribute=[]
g = open('./list_attr_celeba.txt', 'r')
text = g.readlines()
text = np.array(text)
attr2idx = dict()
for i, attr in enumerate(text[1].split()):
attr2idx[attr] = i
attr_index = attr2idx['Eyeglasses']#'Eyeglasses'
for i in text[2:]:
value = i.split()
attribute.append(value[attr_index + 1]) #First index is image name
attribute = np.array(attribute,dtype= np.float32)
#print("Converting Label.................")
for i in range(0,len(attribute)):
if (attribute[i] == 1):
ally[i]=1
else:
ally[i]=0
ally = np.array(ally)
########break up data into training, validation, and test sets
train_limit = int(math.floor(0.8 * len(allX)))
validate_limit = int(math.floor(0.1*len(allX)))
#print (train_limit, validate_limit)
X = allX[0:train_limit,:,]
X_validation = allX[(train_limit+1):(train_limit+validate_limit),:,]
X_test = allX[(train_limit+validate_limit+1):,:,]
Y = ally[0:train_limit]
Y_validation = ally[(train_limit+1):(train_limit+validate_limit)]
Y_test = ally[(train_limit+validate_limit+1):]
# encode the Ys
Y = to_categorical(Y, 2)
Y_test = to_categorical(Y_test, 2)
Y_validation = to_categorical(Y_validation, 2)
#take a subset of training dataset to find parameters
x_sm = int(math.floor(0.8 * len(allX))*0.5)
print (x_sm)
X_sm = allX[0:x_sm,:,]
Y_sm = ally[0:x_sm]
Y_sm=to_categorical(Y_sm, 2)
print (X.shape, Y.shape, allX.shape, ally.shape, X_sm.shape)
###################################
# Image transformations
###################################
# normalisation of images
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
###################################
# Define network architecture
###################################
# Input is a 27x33 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, 27, 33, 3])
#,data_preprocessing=img_prep,
#data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
conv_1 = conv_2d(network, 32, 3, activation='relu', name='conv_1')
# 2: Max pooling layer
network = max_pool_2d(conv_1, 2)
# 3: Convolution layer with 64 filters
conv_2 = conv_2d(network, 64, 3, activation='relu', name='conv_2')
#4: Convolution layer with 64 filters
conv_3 = conv_2d(conv_2, 64, 3, activation='relu', name='conv_3')
# 5: Max pooling layer
network = max_pool_2d(conv_3, 2)
# 6: Fully-connected 512 node layer
network = fully_connected(network, 1024, activation='relu')
# 7: Dropout layer to combat overfitting
network = dropout(network, 0.5)
# 8: Fully-connected layer with two outputs
network = fully_connected(network, 2, activation='softmax')
# Configure how the network will be trained
acc = Accuracy(name="Accuracy")
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001, metric=acc)
# Wrap the network in a model object
model = tflearn.DNN(network, checkpoint_path='model_glasses_6.tflearn', max_checkpoints = 3,
tensorboard_verbose = 3, tensorboard_dir='tmp/tflearn_logs/')
###################################
# Train model for 1000 epochs
###################################
model.fit(X_sm, Y_sm, validation_set=(X_validation, Y_validation), batch_size=50,
n_epoch=1000, run_id='model_glasses_6', show_metric=True)
model.save('model_glasses_6_final.tflearn')
# Evaluate model
score = model.evaluate(X_test, Y_test)
print('Test accuarcy: %0.4f%%' % (score[0] * 100))
def test(hist, labels, filenames, img):
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
network = input_data(shape=[None, 64, 64, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
network = conv_2d(network, 32, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 64, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 128, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 64, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 32, 5, activation='relu')
network = max_pool_2d(network, 5)
network = fully_connected(network, 1024, activation='relu')
network = dropout(network, 0.8)
network = fully_connected(network, 2, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=1e-3,
loss='categorical_crossentropy')
clf = joblib.load('neural2_segmented.pkl')
clf_svc = joblib.load('classifier_svc_segmented.pkl')
clf_ran = joblib.load('classifier_ran_segmented.pkl')
model = tflearn.DNN(network,
checkpoint_path='model_cat_dog_7.tflearn',
max_checkpoints=3,
tensorboard_verbose=3,
tensorboard_dir='tmp/tflearn_logs/')
model.load('model_cat_dog_6_final.tflearn')
preds = []
preds_svc = []
preds_ran = []
preds_cnn = []
for i in range(0, hist.shape[0]):
a = hist[i]
a = a.reshape(1, -1)
preds.append(clf.predict(a))
preds_svc.append(clf_svc.predict(a))
preds_ran.append(clf_ran.predict(a))
img[i] = np.reshape(img[i], (1, 64, 64, 3))
img[i] = img[i].astype('float32')
probs = model.predict(img[i])
preds_cnn.append(np.argmax(probs))
#print(clf_svc.predict(a))
counter1 = 0
counter2 = 0
counter3 = 0
counter4 = 0
counter5 = 0
counter6 = 0
counter7 = 0
counter8 = 0
counter9 = 0
counter10 = 0
counter11 = 0
counter12 = 0
final_pred = []
for i in range(0, hist.shape[0]):
#print(preds[i])
#print(labels[i])
if (preds[i] == labels[i]):
counter1 += 1
else:
counter2 += 1
if (preds_svc[i] == labels[i]):
counter3 += 1
else:
counter4 += 1
if (preds_ran[i] == labels[i]):
counter5 += 1
else:
counter6 += 1
if (preds_cnn[i] == labels[i]):
counter11 += 1
else:
counter12 += 1
if ((int(preds[i]) + int(preds_svc[i]) + int(preds_ran[i])) == 3):
final_pred.append(1)
if (int(labels[i]) == 1):
counter9 += 1
else:
counter10 += 1
elif (int(preds[i]) + int(preds_svc[i]) + int(preds_ran[i]) == 0):
final_pred.append(0)
if (int(labels[i]) == 0):
counter9 += 1
else:
counter10 += 1
else:
ok = np.random.randint(1, 2)
final_pred.append(ok)
if (ok == int(labels[i])):
counter9 += 1
else:
counter10 += 1
print(len(final_pred))
if ((int(preds[i]) + int(preds_svc[i]) + int(preds_ran[i])) == 2 or
(int(preds[i]) + int(preds_svc[i]) + int(preds_ran[i])) == 3):
if (int(labels[i]) == 1):
counter7 += 1
else:
counter8 += 1
elif ((int(preds[i]) + int(preds_svc[i]) + int(preds_ran[i])) == 0
or (int(preds[i]) + int(preds_svc[i]) + int(preds_ran[i])) == 1):
if (int(labels[i]) == 0):
counter7 += 1
else:
counter8 += 1
def getint(name):
print(name[0])
basename = name[0].split('.')
return int(basename[0])
final_pred = [
x for (y, x) in sorted(zip(filenames, final_pred), key=getint)
]
filenames = [
y for (y, x) in sorted(zip(filenames, final_pred), key=getint)
]
with open('Resultss.csv', 'w', newline='') as csvfile:
spamwriter = csv.writer(csvfile, delimiter=',')
spamwriter.writerow(["image", "label"])
for i in range(0, len(preds)):
spamwriter.writerow([filenames[i], final_pred[i]])
accuracy = (counter1 / (counter1 + counter2)) * 100
accuracy_svc = (counter3 / (counter3 + counter4)) * 100
accuracy_ran = (counter5 / (counter5 + counter6)) * 100
accuracy_vote = (counter7 / (counter7 + counter8)) * 100
accuracy_unan = (counter9 / (counter9 + counter10)) * 100
accuracy_cnn = (counter11 / (counter11 + counter12)) * 100
print("mlp accuracy: %d" % accuracy)
print("svm accuracy: %d" % accuracy_svc)
print("random forest accuracy: %d" % accuracy_ran)
print("voting accuracy: %d" % accuracy_vote)
print("unanimous voting accuracy: %d" % accuracy_unan)
print("cnn accuracy: %d" % accuracy_cnn)
def main(_):
dirname = os.path.join(FLAGS.buckets, "")
(X, Y), (X_test, Y_test) = load_data(dirname)
print("load data done")
X, Y = shuffle(X, Y)
Y = to_categorical(Y, 10)
Y_test = to_categorical(Y_test, 10)
# Real-time data preprocessing
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_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
# Convolutional network building
network = input_data(shape=[None, 192, 192, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 128, 3, activation='relu')
network = conv_2d(network, 128, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 1024, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 10, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=0)
# model.fit(X, Y, n_epoch=100, shuffle=True, validation_set=(X_test, Y_test),
# show_metric=True, batch_size=96, run_id='cifar10_cnn')
model_path = os.path.join(FLAGS.checkpointDir, "model.tfl")
print(model_path)
model.load(model_path)
# predict_pic = os.path.join(FLAGS.buckets, "bird_mount_bluebird.jpg")
# file_paths = tf.train.match_filenames_once(predict_pic)
# input_file_queue = tf.train.string_input_producer(file_paths)
# reader = tf.WholeFileReader()
# file_path, raw_data = reader.read(input_file_queue)
# img = tf.image.decode_jpeg(raw_data, 3)
# img = tf.image.resize_images(img, [32, 32])
# prediction = model.predict([img])
# print (prediction[0])
predict_pic = os.path.join(FLAGS.buckets, "bird_bullocks_oriole.jpg")
img_obj = file_io.read_file_to_string(predict_pic)
file_io.write_string_to_file("bird_bullocks_oriole.jpg", img_obj)
img = scipy.ndimage.imread("bird_bullocks_oriole.jpg", mode="RGB")
# Scale it to 32x32
img = scipy.misc.imresize(img, (32, 32),
interp="bicubic").astype(np.float32,
casting='unsafe')
# Predict
prediction = model.predict([img])
print(prediction[0])
print(prediction[0])
#print (prediction[0].index(max(prediction[0])))
num = [
'airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog',
'horse', 'ship', 'truck'
]
print("This is a %s" %
(num[prediction[0].tolist().index(max(prediction[0]))]))
def testing(self):
map = {
0: "Bottle without cap",
1: "Random thing",
2: "Bottle with cap"
}
(X, Y), (X_test, Y_test) = self.loadImages()
# Real-time data preprocessing
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_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
# Convolutional network building
network = input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 3, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=3)
model.load('init_model.tflearn')
correct_predictions = 0
wrong_predictions = 0
totalTests = X_test.__len__()
# Run the model on all examples
for i in range(0, totalTests):
prediction = model.predict([X_test[i]])
# print("Prediction: %s" % str(prediction[0]))
maxIndex = np.argmax(prediction)
if maxIndex == Y_test[i]:
correct_predictions += 1
else:
wrong_predictions += 1
print("Wrong prediction, true label is " + str(Y_test[i]) +
" Predicted label is: " + str(maxIndex))
forShow = np.multiply(X_test[i], 100)
forShow = np.asarray(forShow, int)
cv2.imwrite("WrongPrediction" + str(maxIndex) + ".png",
forShow)
correct_percent = correct_predictions / float(totalTests)
wrong_percent = wrong_predictions / float(totalTests)
print("Correct predictions: " + str(correct_predictions))
print("Wrong predictions: " + str(wrong_predictions))
print("Total: " + str(totalTests))
print("Correct percent: " + str(correct_percent))
print("Wrong percent: " + str(wrong_percent))
def getReseau():
size = settings.size
nb_filter = settings.nb_filter
filter_size = settings.filter_size
# Make sure the data is normalized
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping, rotating and blurring the
# images on our data set.
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_blur(sigma_max=3.)
# Define our network architecture:
# Input is a 32x32 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, size, size, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
reseau = settings.reseau
if reseau == 1:
# Step 1: Convolution
network = conv_2d(network, nb_filter, filter_size, activation='relu')
# Step 2: Max pooling
network = max_pool_2d(network, 2)
# Step 3: Convolution again
network = conv_2d(network,
nb_filter * 4,
filter_size,
activation='relu')
# Step 4: Convolution yet again
network = conv_2d(network,
nb_filter * 4,
filter_size,
activation='relu')
# Step 5: Max pooling again
network = max_pool_2d(network, 2)
# Step 6: Fully-connected 512 node neural network
network = fully_connected(network, nb_filter * 16, activation='relu')
# Step 7: Dropout - throw away some data randomly during training to prevent over-fitting
network = dropout(network, 0.5)
elif reseau == 2:
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = fully_connected(network, 512, activation='relu')
elif reseau == 3:
network = conv_2d(network, 32, 3, activation='relu')
network = avg_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = avg_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = avg_pool_2d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
elif reseau == 4:
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 5, padding='valid', activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 5, padding='valid', activation='relu')
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
elif reseau == 5:
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = avg_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = fully_connected(network, 512, activation='relu')
# Step 8: Fully-connected neural network with three outputs (0=isn't a bird, 1=is a bird) to make the final prediction
network = fully_connected(network,
ld.getLabelsNumber(),
activation='softmax')
# Tell tflearn how we want to train the network
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=settings.learning_rate)
# Wrap the network in a model object
# model = tflearn.DNN(network, tensorboard_verbose=0, checkpoint_path='dataviz-classifier.tfl.ckpt')
model = tflearn.DNN(
network, tensorboard_verbose=0
) # , checkpoint_path='data-classifier/dataviz-classifier.tfl.ckpt')
return model
def setup_model(checkpoint_path=None):
img_prep = ImagePreprocessing()
'''
(optional step), you can feed data_preprocessing = None and the network will still train
Data preprocessing is needed to resolve issues such as incompleteness, inconsistency,
and/or lacking in certain behaviours or trends which occur often in real world data
'''
img_prep.add_featurewise_zero_center()
"""
add_samplewise_zero_center.
Zero center every sample with specified mean. If not specified,
the mean is evaluated over all samples.
Arguments:
mean: `float` (optional). Provides a custom mean. If none
provided, it will be automatically caluclated based on
the training dataset. Default: None.
per_channel: `bool`. If True, compute mean per color channel.
Returns:
Nothing.
"""
img_prep.add_featurewise_stdnorm()
"""
add_featurewise_stdnorm.
Scale each sample by the specified standard deviation. If no std
specified, std is evaluated over all samples data.
Arguments:
std: `float` (optional). Provides a custom standard derivation.
If none provided, it will be automatically caluclated based on
the training dataset. Default: None.
per_channel: `bool`. If True, compute std per color channel.
Returns:
Nothing.
"""
# Create extra synthetic training data by flipping, rotating and blurring the
# images on our data set.
img_aug = ImageAugmentation()
'''
(optional step), you can feed data_augmentation = None and the network will still train
Data augmentation increases our data set by performing various operations on images such
as flipping, rotation and blurring. Also, the training becomes better as the network will
be later able to identify blurred images, flipped images, rotated images as well.
'''
img_aug.add_random_flip_leftright()
"""
Randomly flip an image (left to right).
Returns:
Nothing.
"""
img_aug.add_random_rotation(max_angle=25.)
"""
Randomly rotate an image by a random angle (-max_angle, max_angle).
Arguments:
max_angle: `float`. The maximum rotation angle.
Returns:
Nothing.
"""
img_aug.add_random_blur(sigma_max=3.)
"""
Randomly blur an image by applying a gaussian filter with a random
sigma (0., sigma_max).
Arguments:
sigma: `float` or list of `float`. Standard deviation for Gaussian
kernel. The standard deviations of the Gaussian filter are
given for each axis as a sequence, or as a single number,
in which case it is equal for all axes.
Returns:
Nothing.
"""
network = input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# Input is a 32x32 image with 3 color channels (red, green and blue)
# The first placeholder in shape array must be None to denote the batch size
# If not provided, will be added automatically
# print network = Tensor("InputData/X:0", shape=(?, 32, 32, 3), dtype=float32)
"""
This layer is used for inputting (aka. feeding) data to a network.
A TensorFlow placeholder will be used if it is supplied,
otherwise a new placeholder will be created with the given shape.
Either a shape or placeholder must be provided, otherwise an
exception will be raised.
Input:
List of `int` (Shape), to create a new placeholder.
Or
`Tensor` (Placeholder), to use an existing placeholder.
Output:
Placeholder Tensor with given shape.
Arguments:
shape: list of `int`. An array or tuple representing input data shape.
It is required if no placeholder is provided. First element should
be 'None' (representing batch size), if not provided, it will be
added automatically.
placeholder: A Placeholder to use for feeding this layer (optional).
If not specified, a placeholder will be automatically created.
You can retrieve that placeholder through graph key: 'INPUTS',
or the 'placeholder' attribute of this function's returned tensor.
dtype: `tf.type`, Placeholder data type (optional). Default: float32.
data_preprocessing: A `DataPreprocessing` subclass object to manage
real-time data pre-processing when training and predicting (such
as zero center data, std normalization...).
data_augmentation: `DataAugmentation`. A `DataAugmentation` subclass
object to manage real-time data augmentation while training (
such as random image crop, random image flip, random sequence
reverse...).
name: `str`. A name for this layer (optional).
"""
network = conv_2d(network, 32, 3, activation='relu')
# conv_2d(incoming, nb_filter, filter_size, strides=1, padding='same',
# activation='linear', bias=True, weights_init='uniform_scaling',
# bias_init='zeros', regularizer=None, weight_decay=0.001,
# trainable=True, restore=True, reuse=False, scope=None,
# name="Conv2D"):
# Input:
# 4-D Tensor [batch, height, width, in_channels].
# Output:
# 4-D Tensor [batch, new height, new width, nb_filter].
# print network = Tensor("Conv2D/Relu:0", shape=(?, 32, 32, 32), dtype=float32)
'''
Here we're using relu activation function instead of the sigmoid function
that we looked at as relu has reduced likleyhood of the vanishing gradient
that we saw in sigmoid
This particular function takes the previously created network as input, the
number of convolutional filters being 32 with each filter size 3.
[http://cs231n.github.io/convolutional-networks/]
'''
network = max_pool_2d(network, 2)
# max_pool_2d(incoming, kernel_size, strides=None, padding='same',
# name="MaxPool2D"):
# Input:
# 4-D Tensor [batch, height, width, in_channels].
# Output:
# 4-D Tensor [batch, pooled height, pooled width, in_channels].
# print network = Tensor("MaxPool2D/MaxPool:0", shape=(?, 16, 16, 32), dtype=float32)
'''
It is common to periodically insert a Pooling layer in-between successive Conv
layers in a ConvNet architecture. Its function is to progressively reduce the
spatial size of the representation to reduce the amount of parameters and
computation in the network, and hence to also control overfitting.
'''
network = conv_2d(network, 64, 3, activation='relu')
#print network = Tensor("Conv2D_1/Relu:0", shape=(?, 16, 16, 64), dtype=float32)
network = conv_2d(network, 64, 3, activation='relu')
# print network = Tensor("Conv2D_2/Relu:0", shape=(?, 16, 16, 64), dtype=float32)
network = max_pool_2d(network, 2)
# print network = Tensor("MaxPool2D_1/MaxPool:0", shape=(?, 8, 8, 64), dtype=float32)
network = fully_connected(network, 512, activation='relu')
# fully_connected(incoming, n_units, activation='linear', bias=True,
# weights_init='truncated_normal', bias_init='zeros',
# regularizer=None, weight_decay=0.001, trainable=True,
# restore=True, reuse=False, scope=None,
# name="FullyConnected"):
# incoming: `Tensor`. Incoming (2+)D Tensor.
# n_units: `int`, number of units for this layer.
'''
Neurons in a fully connected layer have full connections to all activations in the
previous layer, as seen in regular Neural Networks. Their activations can hence be
computed with a matrix multiplication followed by a bias offset.
'''
# print network = Tensor("FullyConnected/Relu:0", shape=(?, 512), dtype=float32)
network = dropout(network, 0.5)
# it's one of the method to prevent overfitting
""" Dropout.
Outputs the input element scaled up by `1 / keep_prob`. The scaling is so
that the expected sum is unchanged.
Arguments:
incoming : A `Tensor`. The incoming tensor.
keep_prob : A float representing the probability that each element
is kept.
name : A name for this layer (optional).
References:
Dropout: A Simple Way to Prevent Neural Networks from Overfitting.
N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever & R. Salakhutdinov,
(2014), Journal of Machine Learning Research, 5(Jun)(2), 1929-1958.
Links:
[https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf]
(https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf)
"""
# print network = Tensor("Dropout/cond/Merge:0", shape=(?, 512), dtype=float32)
network = fully_connected(network, 2, activation='softmax')
# print network = Tensor("FullyConnected_1/Softmax:0", shape=(?, 2), dtype=float32)
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
"""
Regression.
The regression layer is used in TFLearn to apply a regression (linear or
logistic) to the provided input. It requires to specify a TensorFlow
gradient descent optimizer 'optimizer' that will minimize the provided
loss function 'loss' (which calculate the errors). A metric can also be
provided, to evaluate the model performance.
A 'TrainOp' is generated, holding all information about the optimization
process. It is added to TensorFlow collection 'tf.GraphKeys.TRAIN_OPS'
and later used by TFLearn 'models' classes to perform the training.
An optional placeholder 'placeholder' can be specified to use a custom
TensorFlow target placeholder instead of creating a new one. The target
placeholder is added to the 'tf.GraphKeys.TARGETS' TensorFlow
collection, so that it can be retrieved later.
Additionaly, a list of variables 'trainable_vars' can be specified,
so that only them will be updated when applying the backpropagation
algorithm.
Input:
2-D Tensor Layer.
Output:
2-D Tensor Layer (Same as input).
Arguments:
incoming: `Tensor`. Incoming 2-D Tensor.
placeholder: `Tensor`. This regression target (label) placeholder.
If 'None' provided, a placeholder will be added automatically.
You can retrieve that placeholder through graph key: 'TARGETS',
or the 'placeholder' attribute of this function's returned tensor.
optimizer: `str` (name), `Optimizer` or `function`. Optimizer to use.
Default: 'adam' (Adaptive Moment Estimation).
loss: `str` (name) or `function`. Loss function used by this layer
optimizer. Default: 'categorical_crossentropy'.
metric: `str`, `Metric` or `function`. The metric to be used.
Default: 'default' metric is 'accuracy'. To disable metric
calculation, set it to 'None'.
learning_rate: `float`. This layer optimizer's learning rate.
dtype: `tf.types`. This layer placeholder type. Default: tf.float32.
batch_size: `int`. Batch size of data to use for training. tflearn
supports different batch size for every optimizers. Default: 64.
shuffle_batches: `bool`. Shuffle or not this optimizer batches at
every epoch. Default: True.
to_one_hot: `bool`. If True, labels will be encoded to one hot vectors.
'n_classes' must then be specified.
n_classes: `int`. The total number of classes. Only required when using
'to_one_hot' option.
trainable_vars: list of `Variable`. If specified, this regression will
only update given variable weights. Else, all trainale variable
are going to be updated.
restore: `bool`. If False, variables related to optimizers such
as moving averages will not be restored when loading a
pre-trained model.
op_name: A name for this layer optimizer (optional).
Default: optimizer op name.
validation_monitors: `list` of `Tensor` objects. List of variables
to compute during validation, which are also used to produce
summaries for output to TensorBoard. For example, this can be
used to periodically record a confusion matrix or AUC metric,
during training. Each variable should have rank 1, i.e.
shape [None].
validation_batch_size: `int` or None. Specifies the batch
size to be used for the validation data feed.
name: A name for this layer's placeholder scope.
Attributes:
placeholder: `Tensor`. Placeholder for feeding labels.
"""
if checkpoint_path:
model = tflearn.DNN(network,
tensorboard_verbose=3,
checkpoint_path=checkpoint_path)
else:
model = tflearn.DNN(network, tensorboard_verbose=3)
return model
def define_network(size_img, N_classes):
'''
Function for defining a particular convolutional network including
3 convolution layers, and 2x max-pooling, as well as 2x fully connected
Parameters
----------
size_img: number of pixels of images to be used, with shape=(size_img,size_img)
N_classes: The number of output classes/cathegories
'''
###################################
# Image transformations
###################################
# normalisation of images
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
###################################
# Define network architecture
###################################
# Input is a size_imagexsize_image, 3 color channels (red, green and blue)
network = input_data(shape=[None, size_img, size_img, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# 1: Convolution layer 32 filters, each 3x3x3
conv_1 = conv_2d(network, 32, 3, activation='relu', name='conv_1')
# 2: Max pooling layer
network = max_pool_2d(conv_1, 2)
# 3: Convolution layer with 64 filters
conv_2 = conv_2d(network, 64, 3, activation='relu', name='conv_2')
# 4: Once more...
conv_3 = conv_2d(conv_2, 64, 3, activation='relu', name='conv_3')
# 5: Max pooling layer
network = max_pool_2d(conv_3, 2)
# 6: Fully-connected 512 node layer
network = fully_connected(network, 512, activation='relu')
# 7: Dropout layer to combat overfitting
network = dropout(network, 0.5)
# 8: Fully-connected layer N_classes outputs
network = fully_connected(network, N_classes, activation='softmax')
# Configure of Network training
acc = Accuracy(name="Accuracy")
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0005,
metric=acc)
return network
def augmentation(self):
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=90.)
img_aug.add_random_blur(sigma_max=3.)
return img_aug
X, Y, X_test, Y_test = load_CIFAR10(data_path)
X, Y = shuffle(X, Y)
Y = to_categorical(Y, 10)
Y_test = to_categorical(Y_test, 10)
# 实时数据预处理
# Real-time data preprocessing
img_pre = ImagePreprocessing()
img_pre.add_featurewise_zero_center(
) # 零中心化,将每个样本的中心设为零，并指定平均值。如果未指定，则对所有样本求平均值。
img_pre.add_featurewise_stdnorm(
) # STD标准化,按指定的标准偏差缩放每个样本。如果未指定std，则对所有样本数据进行std评估。
# 实时数据扩充
# Real-time data augmentation
img_aug = ImageAugmentation() # 实时数据增强
img_aug.add_random_flip_leftright() # 左右翻转
img_aug.add_random_rotation(max_angle=25.) # 随机旋转
# 卷积网络的建立
# Convolutional network building
network = input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_pre,
data_augmentation=img_aug)
network = conv_2d(network, 32, 3,
activation='relu') # 第一层卷积层。32个卷积核，尺寸3x3，激活函数ReLU
network = max_pool_2d(network, 2) # 最大池化层。滑动窗口步幅为2
network = conv_2d(network, 64, 3, activation='relu') #第二层卷积层，64个卷积核
network = conv_2d(network, 64, 3, activation='relu') #第三层卷积层，64个卷积核
network = max_pool_2d(network, 2) # 最大池化层
network = fully_connected(network, 512, activation='relu') #全连接层，512个神经元
def cnn_model(x_shape, y_shape, archi="AlexNet"):
image_aug = ImageAugmentation()
image_aug.add_random_blur(1)
image_aug.add_random_flip_leftright()
image_aug.add_random_flip_updown()
image_aug.add_random_rotation()
image_aug.add_random_90degrees_rotation()
# AlexNet, replacing local normalization with batch normalization.
if archi == "AlexNet":
net = input_data(shape=[None] + list(x_shape[1:]),
data_augmentation=image_aug)
net = conv_2d(net, 96, 7, strides=2, activation='relu')
net = batch_normalization(net)
net = max_pool_2d(net, 2)
net = dropout(net, 0.8)
net = conv_2d(net, 256, 5, strides=2, activation='relu')
net = batch_normalization(net)
net = max_pool_2d(net, 2)
net = dropout(net, 0.8)
net = conv_2d(net, 384, 3, activation='relu')
net = conv_2d(net, 384, 3, activation='relu')
net = conv_2d(net, 256, 3, activation='relu')
net = batch_normalization(net)
net = max_pool_2d(net, 2)
net = dropout(net, 0.8)
net = fully_connected(net, 4096, activation='tanh')
net = dropout(net, 0.5)
net = fully_connected(net, 4096, activation='tanh')
net = dropout(net, 0.5)
net = fully_connected(net, y_shape[1], activation='softmax')
net = regression(net,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0001)
# ResNet, with dropout.
if archi == "ResNet":
n = 5
net = tflearn.input_data(shape=[None] + list(x_shape[1:]),
data_augmentation=image_aug)
net = tflearn.conv_2d(net,
16,
5,
strides=2,
regularizer='L2',
weight_decay=0.0001)
net = tflearn.residual_block(net, n, 16)
net = tflearn.residual_block(net, 1, 32, downsample=True)
net = tflearn.dropout(net, 0.8)
net = tflearn.residual_block(net, n - 1, 32)
net = tflearn.residual_block(net, 1, 64, downsample=True)
net = tflearn.dropout(net, 0.8)
net = tflearn.residual_block(net, n - 1, 64)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
net = tflearn.fully_connected(net, y_shape[1], activation='softmax')
net = tflearn.regression(net,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0001)
return net
def getModel(size_image, is_dropout, learning_rate, is_batch_norm):
###################################
# Image transformations
###################################
# normalisation of images
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
print ("----Begin data augmentation ----------")
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
print ("----End data augmentation ----------")
###########################################################################
################################### Define NETWORK ARCHITECTURE ###########
###########################################################################
# winit = tflearn.initializations.uniform(minval=0, maxval=None, seed=0)
# Input is a 16x16 image
input_layer = input_data(shape=[None, size_image, size_image, 1],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
conv_1 = conv_2d(input_layer, 32, 3, activation='relu', name='conv_1' )
# 2: Convolution layer with 32 filters
conv_2 = conv_2d(conv_1, 32, 3, activation='relu', name='conv_2' )
# 3: Max pooling layer
mp1 = max_pool_2d(conv_2, 2)
# Batch normalization
if is_batch_norm : mp1 = tflearn.normalization.batch_normalization(mp1)
# 4: Convolution layer with 32 filters
conv_3 = conv_2d(mp1, 32, 3, activation='relu', name='conv_3' )
# 5: Convolution layer with 32 filters
conv_4 = conv_2d(conv_3, 32, 3, activation='relu', name='conv_4' )
# 5: Max pooling layer
mp2 = max_pool_2d(conv_4, 2)
# Batch normalization
if is_batch_norm : mp2 = tflearn.normalization.batch_normalization(mp2)
# 6: Fully-connected 256 node layer
dense1 = fully_connected(mp2, 256, activation='relu' )
# 7: Dropout layer to combat overfitting
dp1 = dropout(dense1, 0.5) if is_dropout else dense1
dense2 = fully_connected(dp1, 256, activation='relu' )
dp2 = dropout(dense2, 0.5) if is_dropout else dense2
# 8: Fully-connected layer with 1 outputs ( binary)
network = fully_connected(dp2, 2, activation='softmax' )
# Configure how the network will be trained
gd = tflearn.SGD(learning_rate=learning_rate, lr_decay=0.96, decay_step=500)
network = regression(network, optimizer=gd, loss='categorical_crossentropy', shuffle_batches=True)
# Wrap the network in a model object
model = tflearn.DNN(network, tensorboard_verbose=0)
return model
def build_network(output_dims=[20, 100],
get_hidden_reps=False,
get_fc_softmax_activations=False):
assert (
len(output_dims) == 2
), "output_dims needs to be of length 2, containing coarse_dim and fine_dim."
# outputdims is a list of num_classes
coarse_dim, fine_dim = tuple(output_dims)
# Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
network = input_data(shape=[None, 32, 32, 3], data_augmentation=img_aug)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
coarse_network = conv_2d(network,
64,
3,
activation='relu',
name="unique_conv_1_coarse")
coarse_network = conv_2d(coarse_network,
64,
3,
activation='relu',
name="unique_conv_2_coarse")
coarse_network = max_pool_2d(coarse_network, 2)
coarse_network = fully_connected(coarse_network,
512,
activation='relu',
name="unique_fc_1_coarse")
coarse_hidden_reps = coarse_network
coarse_network = dropout(coarse_network, 0.5)
coarse_network = fully_connected(coarse_network,
coarse_dim,
activation='softmax',
name="unique_fc_2_coarse")
fine_network = conv_2d(network,
64,
3,
activation='relu',
name="unique_conv_1_fine")
fine_network = conv_2d(fine_network,
64,
3,
activation='relu',
name="unique_conv_2_fine")
fine_network = max_pool_2d(fine_network, 2)
fine_network = fully_connected(fine_network,
512,
activation='relu',
name="unique_fc_1_fine")
fine_hidden_reps = fine_network
fine_network = dropout(fine_network, 0.5)
fine_network = fully_connected(fine_network,
fine_dim,
activation='softmax',
name="unique_fc_2_fine")
if get_hidden_reps:
return (coarse_hidden_reps, fine_hidden_reps)
if get_fc_softmax_activations:
# return the last layer of the coarse and the fine branch.
# needed so we can write a custom function which takes the activations, computes the confidence scores and
# decides at what level of the hierarchy to predict.
return (coarse_network, fine_network)
# coarse_confidence =
# fine_confidence =
stacked_coarse_and_fine_net = tf.concat(1, [coarse_network, fine_network])
target_placeholder = tf.placeholder(dtype=tf.float32,
shape=(None, coarse_dim + fine_dim))
def coarse_and_fine_joint_loss(incoming, placeholder):
# coarse_dim = 20
# fine_dim = 40
# has access to coarse_dim and fine_dim
coarse_pred = incoming[:, :coarse_dim]
fine_pred = incoming[:, coarse_dim:]
coarse_target = placeholder[:, :coarse_dim]
fine_target = placeholder[:, coarse_dim:]
coarse_loss = tflearn.categorical_crossentropy(coarse_pred,
coarse_target)
fine_loss = tflearn.categorical_crossentropy(fine_pred, fine_target)
return coarse_loss + fine_loss
def coarse_and_fine_accuracy(y_pred, y_true, x):
coarse_pred = y_pred[:, :coarse_dim]
fine_pred = y_pred[:, coarse_dim:]
coarse_target = y_true[:, :coarse_dim]
fine_target = y_true[:, coarse_dim:]
coarse_acc = tflearn.metrics.accuracy_op(coarse_pred, coarse_target)
fine_acc = tflearn.metrics.accuracy_op(fine_pred, fine_target)
# rounded_coarse_acc = tf.to_float(tf.round(coarse_acc * 1000) * 100000)
# return tf.add(rounded_coarse_acc, fine_acc)
return fine_acc
joint_network = regression(stacked_coarse_and_fine_net,
placeholder=target_placeholder,
optimizer='adam',
loss=coarse_and_fine_joint_loss,
metric=coarse_and_fine_accuracy,
learning_rate=0.001)
return joint_network
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_90degrees_rotation(rotations=[0, 2])
network = input_data(shape=img_shape,
name=name,
data_preprocessing=img_prep,
data_augmentation=img_aug)
conv1_7_7 = conv_2d(network,
64,
7,
strides=2,
activation='relu',
name='conv1_7_7_s2')
pool1_3_3 = max_pool_2d(conv1_7_7, 3, strides=2)
pool1_3_3 = local_response_normalization(pool1_3_3)
conv2_3_3_reduce = conv_2d(pool1_3_3,
64,
1,
activation='relu',
name='conv2_3_3_reduce')
conv2_3_3 = conv_2d(conv2_3_3_reduce,
192,
3,
activation='relu',
name='conv2_3_3')
conv2_3_3 = local_response_normalization(conv2_3_3)
pool2_3_3 = max_pool_2d(conv2_3_3,
kernel_size=3,
strides=2,
name='pool2_3_3_s2')
inception_3a_1_1 = conv_2d(pool2_3_3,
64,
1,
activation='relu',
name='inception_3a_1_1')
inception_3a_3_3_reduce = conv_2d(pool2_3_3,
96,
1,
activation='relu',
name='inception_3a_3_3_reduce')
inception_3a_3_3 = conv_2d(inception_3a_3_3_reduce,
128,
filter_size=3,
activation='relu',
name='inception_3a_3_3')
inception_3a_5_5_reduce = conv_2d(pool2_3_3,
16,
filter_size=1,
activation='relu',
name='inception_3a_5_5_reduce')
inception_3a_5_5 = conv_2d(inception_3a_5_5_reduce,
32,
filter_size=5,
activation='relu',
name='inception_3a_5_5')
inception_3a_pool = max_pool_2d(
pool2_3_3,
kernel_size=3,
strides=1,
)
inception_3a_pool_1_1 = conv_2d(inception_3a_pool,
32,
filter_size=1,
activation='relu',
name='inception_3a_pool_1_1')
# merge the inception_3a__
inception_3a_output = merge([
inception_3a_1_1, inception_3a_3_3, inception_3a_5_5,
inception_3a_pool_1_1
],
mode='concat',
axis=3)
inception_3b_1_1 = conv_2d(inception_3a_output,
128,
filter_size=1,
activation='relu',
name='inception_3b_1_1')
inception_3b_3_3_reduce = conv_2d(inception_3a_output,
128,
filter_size=1,
activation='relu',
name='inception_3b_3_3_reduce')
inception_3b_3_3 = conv_2d(inception_3b_3_3_reduce,
192,
filter_size=3,
activation='relu',
name='inception_3b_3_3')
inception_3b_5_5_reduce = conv_2d(inception_3a_output,
32,
filter_size=1,
activation='relu',
name='inception_3b_5_5_reduce')
inception_3b_5_5 = conv_2d(inception_3b_5_5_reduce,
96,
filter_size=5,
name='inception_3b_5_5')
inception_3b_pool = max_pool_2d(inception_3a_output,
kernel_size=3,
strides=1,
name='inception_3b_pool')
inception_3b_pool_1_1 = conv_2d(inception_3b_pool,
64,
filter_size=1,
activation='relu',
name='inception_3b_pool_1_1')
#merge the inception_3b_*
inception_3b_output = merge([
inception_3b_1_1, inception_3b_3_3, inception_3b_5_5,
inception_3b_pool_1_1
],
mode='concat',
axis=3,
name='inception_3b_output')
pool3_3_3 = max_pool_2d(inception_3b_output,
kernel_size=3,
strides=2,
name='pool3_3_3')
inception_4a_1_1 = conv_2d(pool3_3_3,
192,
filter_size=1,
activation='relu',
name='inception_4a_1_1')
inception_4a_3_3_reduce = conv_2d(pool3_3_3,
96,
filter_size=1,
activation='relu',
name='inception_4a_3_3_reduce')
inception_4a_3_3 = conv_2d(inception_4a_3_3_reduce,
208,
filter_size=3,
activation='relu',
name='inception_4a_3_3')
inception_4a_5_5_reduce = conv_2d(pool3_3_3,
16,
filter_size=1,
activation='relu',
name='inception_4a_5_5_reduce')
inception_4a_5_5 = conv_2d(inception_4a_5_5_reduce,
48,
filter_size=5,
activation='relu',
name='inception_4a_5_5')
inception_4a_pool = max_pool_2d(pool3_3_3,
kernel_size=3,
strides=1,
name='inception_4a_pool')
inception_4a_pool_1_1 = conv_2d(inception_4a_pool,
64,
filter_size=1,
activation='relu',
name='inception_4a_pool_1_1')
inception_4a_output = merge([
inception_4a_1_1, inception_4a_3_3, inception_4a_5_5,
inception_4a_pool_1_1
],
mode='concat',
axis=3,
name='inception_4a_output')
inception_4b_1_1 = conv_2d(inception_4a_output,
160,
filter_size=1,
activation='relu',
name='inception_4a_1_1')
inception_4b_3_3_reduce = conv_2d(inception_4a_output,
112,
filter_size=1,
activation='relu',
name='inception_4b_3_3_reduce')
inception_4b_3_3 = conv_2d(inception_4b_3_3_reduce,
224,
filter_size=3,
activation='relu',
name='inception_4b_3_3')
inception_4b_5_5_reduce = conv_2d(inception_4a_output,
24,
filter_size=1,
activation='relu',
name='inception_4b_5_5_reduce')
inception_4b_5_5 = conv_2d(inception_4b_5_5_reduce,
64,
filter_size=5,
activation='relu',
name='inception_4b_5_5')
inception_4b_pool = max_pool_2d(inception_4a_output,
kernel_size=3,
strides=1,
name='inception_4b_pool')
inception_4b_pool_1_1 = conv_2d(inception_4b_pool,
64,
filter_size=1,
activation='relu',
name='inception_4b_pool_1_1')
inception_4b_output = merge([
inception_4b_1_1, inception_4b_3_3, inception_4b_5_5,
inception_4b_pool_1_1
],
mode='concat',
axis=3,
name='inception_4b_output')
inception_4c_1_1 = conv_2d(inception_4b_output,
128,
filter_size=1,
activation='relu',
name='inception_4c_1_1')
inception_4c_3_3_reduce = conv_2d(inception_4b_output,
128,
filter_size=1,
activation='relu',
name='inception_4c_3_3_reduce')
inception_4c_3_3 = conv_2d(inception_4c_3_3_reduce,
256,
filter_size=3,
activation='relu',
name='inception_4c_3_3')
inception_4c_5_5_reduce = conv_2d(inception_4b_output,
24,
filter_size=1,
activation='relu',
name='inception_4c_5_5_reduce')
inception_4c_5_5 = conv_2d(inception_4c_5_5_reduce,
64,
filter_size=5,
activation='relu',
name='inception_4c_5_5')
inception_4c_pool = max_pool_2d(inception_4b_output,
kernel_size=3,
strides=1)
inception_4c_pool_1_1 = conv_2d(inception_4c_pool,
64,
filter_size=1,
activation='relu',
name='inception_4c_pool_1_1')
inception_4c_output = merge([
inception_4c_1_1, inception_4c_3_3, inception_4c_5_5,
inception_4c_pool_1_1
],
mode='concat',
axis=3,
name='inception_4c_output')
inception_4d_1_1 = conv_2d(inception_4c_output,
112,
filter_size=1,
activation='relu',
name='inception_4d_1_1')
inception_4d_3_3_reduce = conv_2d(inception_4c_output,
144,
filter_size=1,
activation='relu',
name='inception_4d_3_3_reduce')
inception_4d_3_3 = conv_2d(inception_4d_3_3_reduce,
288,
filter_size=3,
activation='relu',
name='inception_4d_3_3')
inception_4d_5_5_reduce = conv_2d(inception_4c_output,
32,
filter_size=1,
activation='relu',
name='inception_4d_5_5_reduce')
inception_4d_5_5 = conv_2d(inception_4d_5_5_reduce,
64,
filter_size=5,
activation='relu',
name='inception_4d_5_5')
inception_4d_pool = max_pool_2d(inception_4c_output,
kernel_size=3,
strides=1,
name='inception_4d_pool')
inception_4d_pool_1_1 = conv_2d(inception_4d_pool,
64,
filter_size=1,
activation='relu',
name='inception_4d_pool_1_1')
inception_4d_output = merge([
inception_4d_1_1, inception_4d_3_3, inception_4d_5_5,
inception_4d_pool_1_1
],
mode='concat',
axis=3,
name='inception_4d_output')
inception_4e_1_1 = conv_2d(inception_4d_output,
256,
filter_size=1,
activation='relu',
name='inception_4e_1_1')
inception_4e_3_3_reduce = conv_2d(inception_4d_output,
160,
filter_size=1,
activation='relu',
name='inception_4e_3_3_reduce')
inception_4e_3_3 = conv_2d(inception_4e_3_3_reduce,
320,
filter_size=3,
activation='relu',
name='inception_4e_3_3')
inception_4e_5_5_reduce = conv_2d(inception_4d_output,
32,
filter_size=1,
activation='relu',
name='inception_4e_5_5_reduce')
inception_4e_5_5 = conv_2d(inception_4e_5_5_reduce,
128,
filter_size=5,
activation='relu',
name='inception_4e_5_5')
inception_4e_pool = max_pool_2d(inception_4d_output,
kernel_size=3,
strides=1,
name='inception_4e_pool')
inception_4e_pool_1_1 = conv_2d(inception_4e_pool,
128,
filter_size=1,
activation='relu',
name='inception_4e_pool_1_1')
inception_4e_output = merge([
inception_4e_1_1, inception_4e_3_3, inception_4e_5_5,
inception_4e_pool_1_1
],
axis=3,
mode='concat')
pool4_3_3 = max_pool_2d(inception_4e_output,
kernel_size=3,
strides=2,
name='pool_3_3')
inception_5a_1_1 = conv_2d(pool4_3_3,
256,
filter_size=1,
activation='relu',
name='inception_5a_1_1')
inception_5a_3_3_reduce = conv_2d(pool4_3_3,
160,
filter_size=1,
activation='relu',
name='inception_5a_3_3_reduce')
inception_5a_3_3 = conv_2d(inception_5a_3_3_reduce,
320,
filter_size=3,
activation='relu',
name='inception_5a_3_3')
inception_5a_5_5_reduce = conv_2d(pool4_3_3,
32,
filter_size=1,
activation='relu',
name='inception_5a_5_5_reduce')
inception_5a_5_5 = conv_2d(inception_5a_5_5_reduce,
128,
filter_size=5,
activation='relu',
name='inception_5a_5_5')
inception_5a_pool = max_pool_2d(pool4_3_3,
kernel_size=3,
strides=1,
name='inception_5a_pool')
inception_5a_pool_1_1 = conv_2d(inception_5a_pool,
128,
filter_size=1,
activation='relu',
name='inception_5a_pool_1_1')
inception_5a_output = merge([
inception_5a_1_1, inception_5a_3_3, inception_5a_5_5,
inception_5a_pool_1_1
],
axis=3,
mode='concat')
inception_5b_1_1 = conv_2d(inception_5a_output,
384,
filter_size=1,
activation='relu',
name='inception_5b_1_1')
inception_5b_3_3_reduce = conv_2d(inception_5a_output,
192,
filter_size=1,
activation='relu',
name='inception_5b_3_3_reduce')
inception_5b_3_3 = conv_2d(inception_5b_3_3_reduce,
384,
filter_size=3,
activation='relu',
name='inception_5b_3_3')
inception_5b_5_5_reduce = conv_2d(inception_5a_output,
48,
filter_size=1,
activation='relu',
name='inception_5b_5_5_reduce')
inception_5b_5_5 = conv_2d(inception_5b_5_5_reduce,
128,
filter_size=5,
activation='relu',
name='inception_5b_5_5')
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)
loss = fully_connected(pool5_7_7, class_num, activation='softmax')
network = regression(loss,
optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=LR,
name='targets')
return network
def build_network(n_classes, get_hidden_reps=False):
#assert n_output_units is not None, \
# "You need to specify how many tokens are in the output classification sequence."
# n_classes represents the total number of classes
# input tensor is prefeature_size x n_output_units
n_output_units = 2
prefeature_embedding_size = 512
single_output_token_size = (100 + 20 + 1)
# Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
network = input_data(
shape=[None, 32, 32, 3],
# data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network,
64,
3,
activation='relu',
name="unique_Conv2D_3")
network = conv_2d(network,
64,
3,
activation='relu',
name="unique_Conv2D_4")
network = max_pool_2d(network, 2)
network = fully_connected(network,
512,
activation='relu',
name="unique_FullyConnected")
network = fully_connected(network,
512,
activation='relu',
name="unique_FullyConnected_1")
net = network # can preload weights up until this point to possibly make faster
# Basically, this repeats the input several times to be fed into the LSTM
net = tf.tile(net, [1, n_output_units])
net = tf.reshape(net, [-1, n_output_units, prefeature_embedding_size])
net = tflearn.lstm(
net,
single_output_token_size,
return_seq=True,
name="actuallyunique_lstm"
) # This returns [# of samples, # of timesteps, output dim]
fine_network, coarse_network = net
fine_network = fully_connected(fine_network,
single_output_token_size,
activation='softmax',
name="actuallyunique_fine_fc")
coarse_network = fully_connected(coarse_network,
single_output_token_size,
activation='softmax',
name="actuallyunique_fine_fc")
stacked_coarse_and_fine_net = tf.concat(1, [coarse_network, fine_network])
# We need to split this and attach different losses
target_placeholder = tf.placeholder(dtype=tf.float32,
shape=(None, n_output_units *
single_output_token_size))
def coarse_and_fine_joint_loss(incoming, placeholder):
coarse_pred = incoming[:, :single_output_token_size]
coarse_target = placeholder[:, :single_output_token_size]
coarse_loss = tflearn.categorical_crossentropy(coarse_pred,
coarse_target)
fine_pred = incoming[:, single_output_token_size:]
fine_target = placeholder[:, single_output_token_size:]
fine_loss = tflearn.categorical_crossentropy(fine_pred, fine_target)
return 4 * coarse_loss + fine_loss
def coarse_and_fine_accuracy(y_pred, y_true, x):
raw_predictions = y_pred
raw_predictions = tf.reshape(raw_predictions,
(-1, 2, single_output_token_size))
raw_predictions = tf.argmax(raw_predictions, 2)
raw_corrects = y_true
raw_corrects = tf.reshape(raw_corrects,
(-1, 2, single_output_token_size))
raw_corrects = tf.argmax(raw_corrects, 2)
hierarchical_pred = simplify_to_hierarchical_format(raw_predictions)
hierarchical_target = simplify_to_hierarchical_format(raw_corrects)
hierarchical_corrects = tf.equal(hierarchical_pred,
hierarchical_target)
hierarchical_acc = tf.reduce_mean(tf.cast(hierarchical_corrects,
tf.float32),
name="Hierarchical_accuracy")
return hierarchical_acc
##### To calculate the average accuracy, do:
#####
# coarse_pred = y_pred[:, :single_output_token_size]
# fine_pred = y_pred[:, single_output_token_size:]
# coarse_target = y_true[:, :single_output_token_size]
# fine_target = y_true[:, single_output_token_size:]
#
# coarse_acc = tflearn.metrics.accuracy_op(coarse_pred, coarse_target)
# fine_acc = tflearn.metrics.accuracy_op(fine_pred, fine_target)
# return (fine_acc + coarse_acc) / 2.0
#####
#####
## LISA --- All this code isn't required to be here.... but after taking 6 hours to figure out how to make this
## work... it felt wrong to delete all of this... lol
# rounded_coarse_acc = tf.to_float(tf.round(coarse_acc * 1000) * 100000)
# return tf.add(rounded_coarse_acc, fine_acc)
#with tf.Graph().as_default():
#import tflearn.helpers.summarizer as s
#s.summarize(coarse_acc, 'scalar', "test_summary")
#summaries.get_summary(type, name, value, summary_collection)
#tflearn.summaries.get_summary("scalar", "coarse_acc", coarse_acc, "test_summary_collection")
#tflearn.summaries.get_summary("scalar", "fine_acc", fine_acc, "test_summary_collection")
#summaries.add_gradients_summary(grads, "", "", summary_collection)
#sum1 = tf.scalar_summary("coarse_acc", coarse_acc)
#tf.merge_summary([sum1])
#tf.merge_summary(tf.get_collection("test_summary_collection"))
#tflearn.summaries.get_summary("scalar", "coarse_acc", coarse_acc)
#tflearn.summaries.get_summary("scalar", "fine_acc", fine_acc)
#tf.scalar_summary("fine_acc", fine_acc)
#tf_summarizer.summarize(coarse_acc, "scalar", "Coarse_accuracy")
#tf_summarizer.summarize(fine_acc, "scalar", "Fine_accuracy")
#test_const = tf.constant(32.0, name="custom_constant")
#sum1 = tf.scalar_summary("dumb_contant", test_const)
#tf.merge_summary([sum1])
# Class predictions are in the form [[A, B], ...], where A=Coarse, B=Fine
def simplify_to_hierarchical_format(class_labels, end_token=120):
fine_labels = class_labels[:, 1]
coarse_labels = class_labels[:, 0]
coarse_labels_mask = tf.cast(tf.equal(fine_labels, end_token),
tf.int64)
coarse_labels_to_permit = coarse_labels * coarse_labels_mask
fine_labels_mask = tf.cast(tf.not_equal(fine_labels, end_token),
tf.int64)
fine_labels_to_permit = fine_labels * fine_labels_mask
hierarchical_labels = coarse_labels_to_permit + fine_labels_to_permit
return hierarchical_labels
with tf.name_scope('Accuracy'):
with tf.name_scope('Coarse_Accuracy'):
coarse_pred = coarse_network
coarse_target = target_placeholder[:, :single_output_token_size]
correct_coarse_pred = tf.equal(tf.argmax(coarse_pred, 1),
tf.argmax(coarse_target, 1))
coarse_acc_value = tf.reduce_mean(
tf.cast(correct_coarse_pred, tf.float32))
with tf.name_scope('Fine_Accuracy'):
fine_pred = fine_network
fine_target = target_placeholder[:, single_output_token_size:]
correct_fine_pred = tf.equal(tf.argmax(fine_pred, 1),
tf.argmax(fine_target, 1))
fine_acc_value = tf.reduce_mean(
tf.cast(correct_fine_pred, tf.float32))
with tf.name_scope('Combination_Accuracies'):
with tf.name_scope('Both_Correct_Accuracy'):
both_correct_acc_value = tflearn.metrics.accuracy_op(
stacked_coarse_and_fine_net, target_placeholder)
with tf.name_scope('Average_Accuracy'):
avg_acc_value = (coarse_acc_value + fine_acc_value) / 2
with tf.name_scope('Hierarchical_Accuracy'):
raw_predictions = stacked_coarse_and_fine_net
raw_predictions = tf.reshape(raw_predictions,
(-1, 2, single_output_token_size))
raw_predictions = tf.argmax(raw_predictions, 2)
raw_corrects = target_placeholder
raw_corrects = tf.reshape(raw_corrects,
(-1, 2, single_output_token_size))
raw_corrects = tf.argmax(raw_corrects, 2)
hierarchical_pred = simplify_to_hierarchical_format(
raw_predictions)
hierarchical_target = simplify_to_hierarchical_format(raw_corrects)
hierarchical_corrects = tf.equal(hierarchical_pred,
hierarchical_target)
hierarchical_acc = tf.reduce_mean(
tf.cast(hierarchical_corrects, tf.float32))
# Reduce the prediction and the actual to ONE dimension
net = regression(stacked_coarse_and_fine_net,
placeholder=target_placeholder,
optimizer='adam',
loss=coarse_and_fine_joint_loss,
metric=coarse_and_fine_accuracy,
validation_monitors=[
coarse_acc_value, fine_acc_value,
both_correct_acc_value, avg_acc_value,
hierarchical_acc
],
learning_rate=0.0001)
return net
#np.reshape(labels, (338,338)) #np.reshape(labels_test, (num_testing_images,338)) print(labels) # shuffle images images, labels = shuffle(images, labels) images_test, labels_test = shuffle(images_test, labels_test) # create preprocessor to normalize images img_preprocessor = ImagePreprocessing() img_preprocessor.add_featurewise_zero_center() img_preprocessor.add_featurewise_stdnorm() # distort images img_distortion = ImageAugmentation() # only flip left/right for shape training #img_distortion.add_random_flip_leftright() img_distortion.add_random_rotation(max_angle=360) img_distortion.add_random_blur(sigma_max=1.) ### ### network architecture ### network = input_data(shape=[None, 64, 64, 1], data_preprocessing=img_preprocessor,
def initialize_network():
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping, rotating and blurring the
# images on our data set.
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_blur(sigma_max=3.)
# Define our network architecture:
# Input is a 32x32 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, 128, 128, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
dropout_chance = 0.5
print("Step 1")
# Step 1: Convolution
network = conv_2d(network, 32, 3, activation='relu')
print("Step 2")
# Step 2: Max pooling
network = max_pool_2d(network, 2)
#network = dropout(network, dropout_chance)
print("Step 3")
# Step 3: Convolution again
network = conv_2d(network, 64, 3, activation='relu')
#network = max_pool_2d(network, 2)
#network = dropout(network, dropout_chance)
print("Step 4")
# Step 4: Convolution yet again
network = conv_2d(network, 64, 4, activation='relu')
#network = max_pool_2d(network, 2)
#network = dropout(network, dropout_chance)
print("Step 5")
# Step 5: Max pooling again
network = max_pool_2d(network, 2)
print("Step 6")
# Step 6: Fully-connected 512 node neural network
network = fully_connected(network, 512, activation='relu')
print("Step 7")
# Step 7: Dropout - throw away some data randomly during training to prevent over-fitting
#network = dropout(network, dropout_chance)
# Step 6: Fully-connected 512 node neural network
#network = fully_connected(network, 512, activation='relu')
print("Step 7")
# Step 7: Dropout - throw away some data randomly during training to prevent over-fitting
network = dropout(network, dropout_chance)
print("Step 8")
# Step 8: Fully-connected neural network with two outputs (0=isn't a bird, 1=is a bird) to make the final prediction
network = fully_connected(network, 7, activation='softmax')
print("Step 9")
# Tell tflearn how we want to train the network
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Wrap the network in a model object
model = tflearn.DNN(network, tensorboard_verbose=0)
return model
def createCNN(args):
size_entry_filter = 32
size_mid_filter = 64
filter_size = 3
color_channels = 3
model_main_activation = 'relu'
model_exit_activation = 'softmax'
max_pool_kernel_size = 2
model_learning_rate = 0.001
num_classes = args['num_classes']
###################################
# Image transformations
###################################
# normalisation of images
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_blur(sigma_max=3.)
###################################
# Define network architecture
###################################
# Input is a image_size x image_size image with 3 color channels (red, green and blue)
network = input_data(
shape=[None, args['size'], args['size'], color_channels],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
network = conv_2d(network,
size_entry_filter,
filter_size,
activation=model_main_activation)
# 2: Max pooling layer
network = max_pool_2d(network, max_pool_kernel_size)
# 3: Convolution layer with 64 filters
network = conv_2d(network,
size_mid_filter,
filter_size,
activation=model_main_activation)
# 4: Convolution layer with 64 filters
network = conv_2d(network,
size_mid_filter,
filter_size,
activation=model_main_activation)
# 5: Max pooling layer
network = max_pool_2d(network, max_pool_kernel_size)
# 6: Convolution layer with 64 filters
network = conv_2d(network,
size_mid_filter,
filter_size,
activation=model_main_activation)
# 7: Convolution layer with 64 filters
network = conv_2d(network,
size_mid_filter,
filter_size,
activation=model_main_activation)
# 8: Max pooling layer
network = max_pool_2d(network, max_pool_kernel_size)
# 9: Fully-connected 512 node layer
network = fully_connected(network, 512, activation=model_main_activation)
# 10: Dropout layer to combat overfitting
network = dropout(network, 0.5)
# 11: Fully-connected layer with two outputs
network = fully_connected(network,
num_classes,
activation=model_exit_activation)
# Configure how the network will be trained
acc = Accuracy(name="Accuracy")
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=model_learning_rate,
metric=acc)
#main_dir = os.path.dirname(os.path.dirname(os.getcwd()))
# Wrap the network in a model object
model = tflearn.DNN(network,
tensorboard_verbose=0,
max_checkpoints=2,
best_checkpoint_path=os.path.join(
os.path.dirname(os.path.dirname(os.getcwd())),
args['id'] + '.tfl.ckpt'),
best_val_accuracy=args['accuracy'])
return model
def label_on_fly(im, model_name,cwd_checkpoint, stride, box_size):
'''Converts pixels of image into labels
Goes through smaller image and prepares it in the same way the images
were prepared for training the model which will be used to predict a label
Goes through the image line by line to avoid using too much memory
:param PIL image im: for prediction,
:parammodel to load,
:param path to model,
:param stride of scanning image
:param box_size
:return: rgb values of the label for each pixel
:rtype: int tuples
'''
input_size = box_size
kernel_size = get_kernel_size(input_size)
# Real-time data preprocessing
im_prep = ImagePreprocessing()
im_prep.add_featurewise_zero_center()
im_prep.add_featurewise_stdnorm()
# Real-time data augmentation
im_aug = ImageAugmentation()
im_aug.add_random_flip_leftright()
im_aug.add_random_rotation(max_angle=360.)
im_aug.add_random_blur(sigma_max=3.)
im_aug.add_random_flip_updown()
# Convolutional network building
network = input_data(shape=[None, input_size, input_size, 3],
data_preprocessing=im_prep,
data_augmentation=im_aug)
network = conv_2d(network, input_size/2, kernel_size, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, input_size, kernel_size, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, input_size*2, kernel_size, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, input_size*2*2, kernel_size, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 6, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Defining model
model = tflearn.DNN(network, tensorboard_verbose=0,tensorboard_dir=cwd_checkpoint,checkpoint_path=cwd_checkpoint)
print('Loading model:', model_name)
model.load(model_name)
print('Sucessfully loaded model')
max_box_size = box_size
labels_predcited = []
#Define the width and the height of the image to be cut up in smaller images
width, height = im.size
box = 0.2*width,0.2*height,0.8*width,0.8*height
im = im.crop(box)
width, height = im.size
#Go through the height (y-axes) of the image
for i in xrange(int((height-max_box_size)/stride)):
center_point_y = max_box_size/2+i*stride
im_temp = []
predictions_temp = []
labels_temp = []
#Go through the width (x-axes) of the image using the same centerpoint independent of boxsize
for j in xrange(int((width- max_box_size)/stride)):
center_point_x = max_box_size/2+j*stride
box = center_point_x-box_size/2, center_point_y-box_size/2, center_point_x+box_size/2,center_point_y+box_size/2
im_temp.append(im.crop(box))
predictions_temp = model.predict(im_temp)
#labels_temp = [colorizer(get_label_from_cnn(predictions_temp[k])) for k in xrange(len(predictions_temp))]
labels_temp = [get_label_from_cnn(predictions_temp[k]) for k in xrange(len(predictions_temp))]
labels_predcited.append(labels_temp)
print('Line %s done' % str(i))
labels_final = [item for m in xrange(len(labels_predcited)) for item in labels_predcited[m]]
return(labels_final)
def test(filenames, img):
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
network = input_data(shape=[None, 64, 64, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
network = conv_2d(network, 32, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 64, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 128, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 64, 5, activation='relu')
network = max_pool_2d(network, 5)
network = conv_2d(network, 32, 5, activation='relu')
network = max_pool_2d(network, 5)
network = fully_connected(network, 1024, activation='relu')
network = dropout(network, 0.8)
network = fully_connected(network, 2, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=1e-3,
loss='categorical_crossentropy')
model = tflearn.DNN(network,
checkpoint_path='model_cat_dog_7.tflearn',
max_checkpoints=3,
tensorboard_verbose=3,
tensorboard_dir='tmp/tflearn_logs/')
model.load('model_cat_dog_6_final.tflearn')
preds_cnn = []
final_pred = []
for i in range(0, len(img)):
img[i] = np.reshape(img[i], (1, 64, 64, 3))
img[i] = img[i].astype('float32')
probs = model.predict(img[i])
preds_cnn.append(np.argmax(probs))
final_pred.append(np.argmax(probs))
def getint(name):
basename = name[0].split('.')
return int(basename[0])
final_pred = [
x for (y, x) in sorted(zip(filenames, final_pred), key=getint)
]
filenames = [
y for (y, x) in sorted(zip(filenames, final_pred), key=getint)
]
with open('Results.csv', 'w', newline='') as csvfile:
spamwriter = csv.writer(csvfile, delimiter=',')
spamwriter.writerow(["image", "label"])
for i in range(0, len(final_pred)):
spamwriter.writerow([filenames[i], final_pred[i]])
def evaluate(index, zone):
if (not os.path.isfile('models/zone' + str(zone) + '/' + str(index) +
'/checkpoint')):
return [], [], []
# Same network definition as before
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_blur(sigma_max=3.)
#adding here
if (zone == 13 or zone == 14):
dimX = 256
dimY = 75
elif (zone == 11 or zone == 12):
dimX = 256
dimY = 75
elif (zone == 10):
dimX = 237
dimY = 80
elif (zone == 9):
dimX = 50
dimY = 80
elif (zone == 8):
if (index == 1 or index == 13):
dimX = 225
dimY = 80
elif (index == 9):
dimX = 237
dimY = 80
elif (zone == 6 or zone == 7):
dimX = 256
dimY = 60
elif (zone == 5):
dimX = 512
dimy = 80
else:
dimX = 0
dimY = 0
network = input_data(
shape=[None, dimY, dimX, 1], #zone14,13
#network = input_data(shape=[None, 80, 512, 1], #zone5
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 2, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='models/zone' + str(zone) + '/' +
str(index) + '/TSA-Zone' + str(zone) + '-Angle-' +
str(index) + '.tfl') #zone14
model.load("models/zone" + str(zone) + "/" + str(index) + "/TSA-Zone" +
str(zone) + "-Angle-" + str(index) + ".tfl") #zone14
apsid = []
predArray = []
bnotb = []
mypath = "../aps/test_data/"
onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]
tp = 0
tn = 0
fp = 0
fn = 0
for fname in onlyfiles:
if fname.endswith(".aps"):
# Load the image file
#img = scipy.ndimage.imread(args.image, mode="RGB")
apsid.append(fname.split('.')[0])
single_image = sg.get_single_image("../aps/test_data/" + fname,
index)
img = sg.convert_to_grayscale(single_image)
crop_dim = sg.get_crop_dimensions(index, zone)
img = img[crop_dim[0]:crop_dim[1], crop_dim[2]:crop_dim[3]]
img = np.asfarray(img).reshape(dimY, dimX, 1) #zone14,13
# Predict
prediction = model.predict([img])
#print(prediction)
predArray.append(prediction)
# Check the result.
is_threat = np.argmax(prediction[0]) == 1
bnotb.append(is_threat)
final_result = []
filename = 'test_labels.csv'
with open(filename) as csvfile:
readCSV = csv.reader(csvfile, delimiter=',')
for row in readCSV:
final_result.append(row)
if is_threat:
print("That's detetced: " + str(fname))
flag = True
for value in final_result:
if value[0] + ".aps" == fname:
label = int(value[1])
if zone == label:
tp = tp + 1
flag = False
break
if flag:
fp = fp + 1
else:
flag = True
for value in final_result:
if value[0] + ".aps" == fname:
label = int(value[1])
if zone == label:
fn = fn + 1
flag = False
break
if flag:
tn = tn + 1
print('True positives', tp)
print('False positives', fp)
print('True negatives', tn)
print('False negatives', fn)
return apsid, predArray, bnotb
X_test = np.load("TEST.npy")
Y_test = np.load("TEST_LABEL.npy")
print("Total size :", len(X) + len(X_test))
print("Total train :", len(X))
print("Total test :", len(X_test))
###################################
# Image transformations
###################################
# normalisation of images
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
###################################
# Define network architecture
###################################
# Input is a 32x32 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, 64, 64, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
conv_1 = conv_2d(network, 32, 3, activation='relu', name='conv_1')
def define_network(self):
"""
Defines CNN architecture
:return: CNN model
"""
# My CNN 1 (type1)
# # For data normalization
# img_prep = ImagePreprocessing()
# img_prep.add_featurewise_zero_center()
# img_prep.add_featurewise_stdnorm()
#
# # For creating extra data(increase dataset). Flipped, Rotated, Blurred and etc. images
# img_aug = ImageAugmentation()
# img_aug.add_random_flip_leftright()
# img_aug.add_random_rotation(max_angle=25.0)
# img_aug.add_random_blur(sigma_max=3.0)
#
# self.network = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1],
# data_augmentation=img_aug,
# data_preprocessing=img_prep)
# self.network = conv_2d(self.network, 64, 5, activation='relu')
# self.network = max_pool_2d(self.network, 3, strides=2)
# self.network = conv_2d(self.network, 64, 5, activation='relu')
# self.network = max_pool_2d(self.network, 3, strides=2)
# self.network = conv_2d(self.network, 128, 4, activation='relu')
# self.network = dropout(self.network, 0.3)
# self.network = fully_connected(self.network, 3072, activation='relu')
# self.network = fully_connected(self.network, len(EMOTIONS), activation='softmax')
# self.network = regression(self.network, optimizer='adam', loss='categorical_crossentropy')
# self.model = tflearn.DNN(self.network, checkpoint_path=os.path.join(CHECKPOINTS_PATH + '/emotion_recognition'),
# max_checkpoints=1, tensorboard_verbose=0)
# My CNN 2 (type2)
# For creating extra data(increase dataset). Flipped, Rotated, Blurred and etc. images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.0)
img_aug.add_random_blur(sigma_max=3.0)
self.network = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1],
data_augmentation=img_aug)
self.network = conv_2d(self.network, 64, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 64, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = conv_2d(self.network, 128, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 128, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = dropout(self.network, 0.2)
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = dropout(self.network, 0.25)
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = dropout(self.network, 0.25)
self.network = fully_connected(self.network, 1024, activation='relu')
self.network = batch_normalization(self.network)
self.network = dropout(self.network, 0.45)
self.network = fully_connected(self.network, 1024, activation='relu')
self.network = batch_normalization(self.network)
self.network = dropout(self.network, 0.45)
self.network = fully_connected(self.network,
len(EMOTIONS),
activation='softmax')
self.network = regression(self.network,
optimizer='adam',
loss='categorical_crossentropy')
self.model = tflearn.DNN(
self.network,
checkpoint_path=os.path.join(CHECKPOINTS_PATH +
'/emotion_recognition'),
max_checkpoints=1,
tensorboard_verbose=0)
return self.model
