def net_nodule2d_swethasubramanian(image_dims):
#image augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_flip_updown()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_blur(sigma_max=3.)
#image pre-processing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
net = layers.core.input_data(shape=[None, image_dims[0], image_dims[1], image_dims[2], image_dims[3]], dtype=tf.float32, data_preprocessing=img_prep, data_augmentation=img_aug)
net = layers.conv.conv_2d(net, 50, 3, activation='relu')
net = layers.conv.max_pool_2d(net, 2)
net = layers.conv.conv_2d(net, 64, 3, activation='relu')
net = layers.conv.conv_2d(net, 64, 3, activation='relu')
net = layers.conv.max_pool_2d(net, 2)
net = layers.core.fully_connected(net, 512, activation='relu')
net = layers.core.dropout(net, 0.5)
net = layers.core.fully_connected(net, 2, activation='softmax')
net = layers.estimator.regression(net, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
return net
def network(img_shape, name, LR):
# # 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_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)
# def rete(img_shape, name, LR):
# network = input_data(shape=img_shape, name=name)
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, 2, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=LR,
name='targets')
return 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_flip_leftright()
img_aug.add_random_flip_updown()
img_aug.add_random_90degrees_rotation(rotations=[0, 2])
# Building 'AlexNet'
network = input_data(shape=img_shape, name=name, data_preprocessing=img_prep, data_augmentation=img_aug )
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 2, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=LR, name='targets')
return network
def train_model(images,labels,input_size,kernel_size,cwd_data,cwd_checkpoint,run_name,num_epoch=40,num_labels=6):
'''Trains a CNN network and saves the trained model in cwd_checkpoint path
:param np.float32 images: RGB images with shape (training_size, input_size, input_size, 3)
:param np.float32 labels: labels with shape (training_size, num_labels)
:param int input_size: width and height of images
:param int kernel_size: kernel size of network
:param str cwd_data: path to data folder
:param str cwd_data: path to checkpoint folder
:param int num_epoch: number of epochs model should train for
:param int num_labels: number of classes the network trains for
'''
# 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=360.)
img_aug.add_random_blur(sigma_max=3.)
img_aug.add_random_flip_updown()
# Convolutional network building
network = input_data(shape=[None, input_size, input_size, 3],
data_preprocessing=img_prep,
data_augmentation=img_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, num_labels, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=0,tensorboard_dir=cwd_data,checkpoint_path=cwd_checkpoint,max_checkpoints=2)
#model.load(cwd_data+'oct-cvn-48bal-6c-114300')
model.fit(images, labels, n_epoch=num_epoch, validation_set=0.1, show_metric=True, run_id=run_name, snapshot_epoch=True)
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])
# Building Residual Network
network = tflearn.input_data(shape=img_shape,
name=name,
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = tflearn.conv_2d(network,
16,
3,
regularizer='L2',
weight_decay=0.0001)
network = tflearn.resnext_block(network, n, 16, 32)
network = tflearn.resnext_block(network, 1, 32, 32, downsample=True)
network = tflearn.resnext_block(network, n - 1, 32, 32)
network = tflearn.resnext_block(network, 1, 64, 32, downsample=True)
network = tflearn.resnext_block(network, n - 1, 64, 32)
network = tflearn.batch_normalization(network)
network = tflearn.activation(network, 'relu')
network = tflearn.global_avg_pool(network)
# Regression
network = tflearn.fully_connected(network, 2, activation='softmax')
opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
network = tflearn.regression(network,
optimizer=opt,
name='targets',
loss='categorical_crossentropy')
return network
XA=np.load('/home/u3749/code/64_rescale_gray_all_images_as_vecs.npy')
YA=np.load('/home/u3749/code/64_rescale_all_image_types.npy')
# 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.)
img_aug.add_random_blur(sigma_max=3.)
img_aug.add_random_flip_updown()
# Convolutional network building
network = input_data(shape=[None, 64, 64, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
#network = input_data(shape=[None, 32, 32, 3])
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, 512, activation='relu',regularizer='L2')
network = dropout(network, 0.5)
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
from __future__ import division, print_function, absolute_import
import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.conv import conv_2d, max_pool_2d, avg_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.merge_ops import merge
from tflearn.layers.estimator import regression
from tflearn.data_utils import image_preloader
from tflearn.data_utils import image_preloader
from tflearn.data_augmentation import ImageAugmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_flip_updown()
img_aug.add_random_crop([224, 224], 10)
img_aug.add_random_blur()
img_aug.add_random_rotation(max_angle=25.)
X,Y = image_preloader('files_list', image_shape = (224,224),mode='file',categorical_labels=True,normalize=True,files_extension=['.jpg', '.jpeg','.png'])
network = input_data(shape=[None, 224, 224, 3],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')
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 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)
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 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
