def simple_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)
conv = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(conv, 2)
conv = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(conv, 2)
conv = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(conv, 2)
conv = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(conv, 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=0.0005)
simple_model = tflearn.DNN(network)
simple_model.load('model\\simple\\jun_simple_cat_dog_final.tflearn')
simple_result = simple_model.predict(X)
return simple_result
def alex_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)
network = conv_2d(network, 64, 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='adam',
loss='categorical_crossentropy',
learning_rate=0.0005)
alex_model = tflearn.DNN(network)
alex_model.load('model\\alex\\jun_ALEX_cat_dog_final.tflearn')
alex_result = alex_model.predict(X)
return alex_result
def _model2():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
net = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
n = 2
j = 64
'''
net = tflearn.conv_2d(net, j, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.residual_block(net, n, j)
net = tflearn.residual_block(net, 1, j*2, downsample=True)
net = tflearn.residual_block(net, n-1, j*2)
net = tflearn.residual_block(net, 1, j*4, downsample=True)
net = tflearn.residual_block(net, n-1, j*4)
net = tflearn.residual_block(net, 1, j*8, downsample=True)
net = tflearn.residual_block(net, n-1, j*8)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
'''
net = tflearn.conv_2d(net, j, 7, strides = 2, regularizer='L2', weight_decay=0.0001)
net = max_pool_2d(net, 2, strides=2)
net = tflearn.residual_block(net, n, j)
net = tflearn.residual_block(net, 1, j*2, downsample=True)
net = tflearn.residual_block(net, n-1, j*2)
net = tflearn.residual_block(net, 1, j*4, downsample=True)
net = tflearn.residual_block(net, n-1, j*4)
net = tflearn.residual_block(net, 1, j*8, downsample=True)
net = tflearn.residual_block(net, n-1, j*8)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
net = tflearn.fully_connected(net, len(yTest[0]), activation='softmax')
mom = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=mom,
loss='categorical_crossentropy')
model = tflearn.DNN(net, checkpoint_path='model2_resnet',
max_checkpoints=10, tensorboard_verbose=3, clip_gradients=0.)
model.load(_path)
pred = model.predict(xTest)
df = pd.DataFrame(pred)
df.to_csv(_path + ".csv")
newList = pred.copy()
newList = convert2(newList)
if _CSV: makeCSV(newList)
pred = convert2(pred)
pred = convert3(pred)
yTest = convert3(yTest)
print(metrics.confusion_matrix(yTest, pred))
print(metrics.classification_report(yTest, pred))
print('Accuracy', accuracy_score(yTest, pred))
print()
if _wrFile: writeTest(pred)
def network():
tflearn.init_graph(num_cores=4, gpu_memory_fraction=0.8)
# Normalization of the data
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create random new data (more you have, better is)
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.)
#Input network must match inputs of the data set
network = input_data(shape=[None, 100, 100, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
"""
Creation of the different hidden layers
================
Editing section
================
"""
network = conv_2d(network, 64, 3, strides=2, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 2, activation='relu')
network = conv_2d(network, 64, 2, activation='relu')
network = max_pool_2d(network, 2)
#Fully connected layer then we drop a part of the data in order to not overfit
network = fully_connected(network, 4096, activation='relu')
network = dropout(network, 0.7)
"""
======================
End of Editing section
======================
"""
network = fully_connected(network, 120, activation='softmax')
# Training hyper-parameters
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
#Creation of the deep neural network with the back up name
#tensorboard_verbose=0 is the most optimal for the calculation time
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='dog_classifier.tfl.ckpt')
return model
def CNN_Model_Creation():
# 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 512x512 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, 512, 512,3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# Step 1: Convolution
network = conv_2d(network, 32, 5, activation='relu')
network = conv_2d(network, 32, 3, activation='relu')
# Step 2: Max pooling
network = max_pool_2d(network, 2)
# Step 3: Convolution again
network = conv_2d(network, 64, 3, activation='relu')
# Step 4: Convolution yet again
network = conv_2d(network, 64, 3, activation='relu')
# Step 5: Max pooling again
network = max_pool_2d(network, 2)
network = conv_2d(network, 96, 2, activation='relu')
network = max_pool_2d(network, 2)
# Step 6: Fully-connected 512 node neural network
network = fully_connected(network, 512, activation='relu')
# Step 7: Dropout - throw away some data randomly during training to prevent over-fitting
network = dropout(network, 0.5)
# Step 8: Fully-connected neural network with two outputs (0=isn't a cancer, 1=is a cancer) to make the final prediction
network = fully_connected(network, 2, activation='softmax')
#momentum = tflearn.optimizers.Momentum(learning_rate=0.05, momentum=0.7, lr_decay=0.5)
# Tell tflearn how we want to train the network
network = regression(network, optimizer='adam',
loss='categorical_crossentropy')
# Wrap the network in a model object
model = tflearn.DNN(network, tensorboard_verbose=0)
return model
def createNetwork(self, input_size):
# 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, input_size, input_size, 3],
# data_preprocessing=img_prep,
# data_augmentation=img_aug)
network = input_data(shape=[None, input_size, input_size, 3])
network = conv_2d(network, input_size, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, input_size * 2, 3, activation='relu')
network = conv_2d(network, input_size * 2, 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, 4, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
return network
def create_network(optimiser):
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_samplewise_stdnorm()
img_prep.add_featurewise_stdnorm()
# Real-time data augmentation to add variance to the data
img_aug = ImageAugmentation()
img_aug.add_random_blur(sigma_max=3)
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, 10, activation='softmax')
network = regression(network,
optimizer=optimiser,
loss='categorical_crossentropy',
learning_rate=0.002)
return network
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_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 data_preprocessing():
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
return img_prep
def build_model():
# 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, 10, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
return tflearn.DNN(network, tensorboard_verbose=0)
def _model1():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 32, 3, strides = 4, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, strides = 2, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, len(Y[0]), activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy', name='target')
model = tflearn.DNN(network, tensorboard_verbose=3)
model.fit(X, Y, n_epoch=epochNum, validation_set=(xTest, yTest),
snapshot_step=500, show_metric=True, batch_size=batchNum, shuffle=True, run_id=_id + 'artClassification')
if modelStore: model.save(_id + '-model.tflearn')
def create_own_model():
# 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.)
convnet = input_data(shape=[None, img_width, img_height, 1],
data_preprocessing=img_prep,
data_augmentation=img_aug)
convnet = conv_2d(convnet, 28, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 28, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = fully_connected(convnet, 512, activation='relu')
oonvnet = dropout(convnet, 0.2)
convnet = fully_connected(convnet, nb_classes, activation='softmax')
model = regression(convnet,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='targets')
return model
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):
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 res_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)
n = 5
net = input_data(shape=[None, 64, 64, 3], data_preprocessing=img_prep, data_augmentation=img_aug)
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.residual_block(net, n, 16)
net = tflearn.residual_block(net, 1, 32, downsample=True)
net = tflearn.residual_block(net, n - 1, 32)
net = tflearn.residual_block(net, 1, 64, downsample=True)
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, 2, activation='softmax')
mom = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=mom,
loss='categorical_crossentropy')
model = tflearn.DNN(net)
# rnn typo -> res
model.load('model\\res\\jun_rnn_cat_dog.tflearn')
res_result = model.predict(X)
return res_result
def build_model():
logging.info('building model')
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
encoder = input_data(shape=(None, IMAGE_INPUT_SIZE[0], IMAGE_INPUT_SIZE[1],
3), data_preprocessing=img_prep)
encoder = conv_2d(encoder, 16, 7, activation='relu')
encoder = dropout(encoder, 0.25) # you can have noisy input instead
encoder = max_pool_2d(encoder, 2)
encoder = conv_2d(encoder, 16, 7, activation='relu')
encoder = max_pool_2d(encoder, 2)
encoder = conv_2d(encoder, 8, 7, activation='relu')
encoder = max_pool_2d(encoder, 2)
decoder = conv_2d(encoder, 8, 7, activation='relu')
decoder = upsample_2d(decoder, 2)
decoder = conv_2d(decoder, 16, 7, activation='relu')
decoder = upsample_2d(decoder, 2)
decoder = conv_2d(decoder, 16, 7, activation='relu')
decoder = upsample_2d(decoder, 2)
decoder = conv_2d(decoder, 3, 7)
encoded_str = re.search(r', (.*)\)', str(encoder.get_shape)).group(1)
encoded_size = np.prod([int(o) for o in encoded_str.split(', ')])
original_img_size = np.prod(IMAGE_INPUT_SIZE) * 3
percentage = round(encoded_size / original_img_size, 2) * 100
logging.debug('the encoded representation is {}% of the original \
image'.format(percentage))
return regression(decoder, optimizer='adadelta',
loss='binary_crossentropy', learning_rate=0.005)
def build_model_anything_happening():
### IS ANY OF THIS NECESSARY FOR LIGHT/DARK? IN GENERAL W/ STAIONARY CAMERA?
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
# Specify shape of the data, image prep
network = input_data(shape=[None, 52, 64],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# Since the image position remains consistent and are fairly similar, this can be spatially aware.
# Using a fully connected network directly, no need for convolution.
network = fully_connected(network, 2048, activation='relu')
network = fully_connected(network, 2, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.00003)
model = tflearn.DNN(network, tensorboard_verbose=0)
return model
def create_model(nb_classes):
# 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.)
network = input_data(shape=[None, 60, 60, 1],
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 30, 3, strides=2, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = conv_2d(network, 30, 3, strides=2, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = fully_connected(network, 128, activation='relu')
network = fully_connected(network, nb_classes, activation='softmax')
model = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
return model
def preprocessing(self):
"""
Make sure the data is normalized
"""
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
return img_prep
def snack_detection_worker():
global snack_image
# image preprocessors for neural network input
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.)
# setting up neural network
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')
#TODO: change checkpoint path
model = tflearn.DNN(network,
checkpoint_path='model_cat_dog_7.tflearn',
max_checkpoints=3,
tensorboard_verbose=3,
tensorboard_dir='tmp/tflearn_logs/')
model.load('reference code/model_cat_dog_6_final.tflearn')
while True:
#print (image)
image = cv2.resize(snack_image, (64, 64))
if (image.all() != 0):
print("detecting snacks")
test(model, image)
def main(_):
print(FLAGS.buckets)
print(FLAGS.checkpointDir)
print(FLAGS.test_para)
if tf.gfile.Exists(FLAGS.checkpointDir):
tf.gfile.DeleteRecursively(FLAGS.checkpointDir)
tf.gfile.MakeDirs(FLAGS.checkpointDir)
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, 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, 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=50,
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.save(model_path)
def run(self):
# Real-time pre-processing of the image data
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Real-time data augmentation
img_aug = tflearn.ImageAugmentation()
img_aug.add_random_flip_leftright()
# Resnet model below: Adapted from tflearn website
self.n = 5 #32 layer resnet
# Building Residual Network
net = tflearn.input_data(shape=[None, 48, 48, 1], data_preprocessing=img_prep, data_augmentation=img_aug)
net = tflearn.conv_2d(net, nb_filter=16, filter_size=3, regularizer='L2', weight_decay=0.0001)
net = tflearn.residual_block(net, self.n, 16)
net = tflearn.residual_block(net, 1, 32, downsample=True)
net = tflearn.residual_block(net, self.n - 1, 32)
net = tflearn.residual_block(net, 1, 64, downsample=True)
net = tflearn.residual_block(net, self.n - 1, 64)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, 7, activation='softmax')
mom = tflearn.Momentum(learning_rate=0.1, lr_decay=0.0001, decay_step=32000, staircase=True, momentum=0.9)
net = tflearn.regression(net, optimizer=mom,
loss='categorical_crossentropy')
self.model = tflearn.DNN(net, checkpoint_path='models/model_resnet_emotion',
max_checkpoints=10, tensorboard_verbose=0,
clip_gradients=0.)
self.model.load('model.tfl')
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(0)
#Main Loop where we will be capturing live webcam feed, crop image and process the image for emotion recognition on trained model
while True:
ret, img = cap.read()
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x, y, w, h) in faces:
cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)
roi_gray = gray[y:y + h, x:x + w]
roi_color = img[y:y + h, x:x + w]
self.image_processing(roi_gray, img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
def build_network(self):
print('---------------------Building CNN---------------------')
img_preProcess=ImagePreprocessing()
img_preProcess.add_featurewise_zero_center()
img_preProcess.add_featurewise_stdnorm()
# Mean: 189.80002318
# STD: 85.4885473338
#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)
self.network = input_data(shape = [None, constants.IMAGE_HEIGHT, constants.IMAGE_WIDTH, 3])
self.network = conv_2d(self.network, 64, 3, activation='relu')
self.network = conv_2d(self.network, 64, 3, activation='relu')
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = conv_2d(self.network, 128, 3, activation='relu')
self.network = conv_2d(self.network, 128, 3, activation='relu')
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = fully_connected(self.network, 4096, activation='relu')
self.network = dropout(self.network, 0.5)
self.network = fully_connected(self.network, 4096, activation='relu')
self.network = dropout(self.network, 0.5)
self.network = fully_connected(self.network, 5, activation='softmax')
self.network = regression(self.network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0001)
self.model = tflearn.DNN(
self.network,
tensorboard_dir=constants.DATA_PATH,
checkpoint_path =constants.DATA_PATH + '/gun_checkpoint',
max_checkpoints = 1,
tensorboard_verbose = 2
)
self.load_model()
print('-----------------------Model Loaded----------------------')
def ANN(WIDTH, HEIGHT, CHANNELS, LABELS):
dropout_value = 0.35
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Building the network
network = input_data(shape=[None, WIDTH, HEIGHT, CHANNELS],
data_preprocessing=img_prep,
name='input')
# Branch 1
branch1 = conv_2d(network,
10, [2, 2],
activation='relu',
name='B1Conv2d_2x2')
#branch1 = dropout(branch1, dropout_value)
# Branch 2
branch2 = conv_2d(branch1,
10, [2, 2],
activation='relu',
name='B2Conv2d_2x2')
#branch2 = dropout(branch2, dropout_value)
# Fully connected 1
full_1 = fully_connected(branch2, 100, activation='relu')
full_1 = dropout(full_1, dropout_value)
# Fully connected 2
full_2 = fully_connected(full_1, 100, activation='relu')
full_2 = dropout(full_2, dropout_value)
# Output layer
network = fully_connected(full_2, LABELS, activation='softmax')
'''
network = tflearn.regression(network, optimizer = 'momentum',
loss = 'categorical_crossentropy',
learning_rate = 0.1)
'''
network = regression(network,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='target')
model = tflearn.DNN(network,
tensorboard_verbose=0,
tensorboard_dir='./logs',
best_checkpoint_path='./checkpoints/best/best_val',
max_checkpoints=1)
return model
def build_net():
n = 5
tflearn.config.init_training_mode()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Real-time data augmentation
img_aug = tflearn.ImageAugmentation()
img_aug.add_random_flip_leftright()
# img_aug.add_random_crop([48, 48], padding=8)
# Building Residual Network
net = tflearn.input_data(shape=[None, 48, 48, 1],
data_preprocessing=img_prep,
data_augmentation=img_aug)
net = tflearn.conv_2d(net,
nb_filter=16,
filter_size=3,
regularizer='L2',
weight_decay=0.0001)
net = tflearn.residual_block(net, n, 16)
net = tflearn.residual_block(net, 1, 32, downsample=True)
net = tflearn.residual_block(net, n - 1, 32)
net = tflearn.residual_block(net, 1, 64, downsample=True)
net = tflearn.residual_block(net, n - 1, 64)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, 7, activation='softmax')
mom = tflearn.Momentum(learning_rate=0.1,
lr_decay=0.0001,
decay_step=32000,
staircase=True,
momentum=0.9)
net = tflearn.regression(net,
optimizer=mom,
loss='categorical_crossentropy')
print("make model")
model = tflearn.DNN(
net,
checkpoint_path='upload/Resmodels/model_resnet_emotion',
max_checkpoints=10,
tensorboard_verbose=0,
clip_gradients=0.)
print("load model start")
model.load('upload/Resmodels/model_resnet_emotion-10500')
print("load model success")
return model
def main(data_dir, hdf5, name):
batch_size = 256
num_epochs = 10
learning_rate = 0.001
X, Y, X_test, Y_test = get_data(data_dir, hdf5)
X, Y = shuffle(X, Y)
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.)
network = input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# Step 1: Convolution
network = conv_2d(network, 32, 3, activation='relu')
# Step 2: Max pooling
network = max_pool_2d(network, 2)
# Step 3: Convolution
network = conv_2d(network, 64, 3, activation='relu')
# Step 4: Convolution
network = conv_2d(network, 64, 3, activation='relu')
# Step 5: Max pooling
network = max_pool_2d(network, 2)
# Step 6: Fully-connected 512 node neural network
network = fully_connected(network, 512, activation='relu')
# Step 7: Dropout - throw away some data randomly during training to prevent over-fitting
network = dropout(network, 0.5)
# 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, 2, activation='softmax')
# 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,
checkpoint_path='bird-classifier.tfl.ckpt')
# Train it! We'll do 100 training passes and monitor it as it goes.
model.fit(X,
Y,
n_epoch=100,
shuffle=True,
validation_set=(X_test, Y_test),
show_metric=True,
batch_size=96,
snapshot_epoch=True,
run_id='bird-classifier')
# Save model when training is complete to a file
model.save("bird-classifier.tfl")
print("Network trained and saved as bird-classifier.tfl!")
def net(X, Y, save_model=False):
tflearn.config.init_graph(gpu_memory_fraction=1)
# Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# use Transfer learning for better performance
# Building convolutional network
network = input_data(shape=[None, 48, 48, 3], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 2, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = conv_2d(network, 2, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 328, activation='relu')
network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='relu')
network = fully_connected(network, 128, activation='relu')
# network = dropout(network, 0.8)
network = fully_connected(network, len(set(Y)) + 1, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=0.001,
loss='softmax_categorical_crossentropy',
name='target')
# Training
model = tflearn.DNN(network, tensorboard_verbose=3)
# print(Y)
print(np.eye(len(set(Y)) + 1)[Y])
model.fit({'input': X}, {'target': np.array(np.eye(len(set(Y)) + 1)[Y])},
n_epoch=15,
batch_size=50,
validation_set=0.3,
snapshot_step=15000,
show_metric=True,
run_id='face_recogn')
if os.path.exists('fr.tflearn.index'):
print('Loading pre-trained model')
model.load('fr.tflearn')
if save_model:
model.save('fr.tflearn')
return model
def build_network(output_dims=None):
# outputdims is a list of num_classes
# 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.)
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)
networks = []
for i, output_dim in enumerate(output_dims):
for j in xrange(i):
network = conv_2d(network,
64,
3,
activation='relu',
name="unique_Conv2D_{}".format(3 + 2 * j))
network = conv_2d(network,
64,
3,
activation='relu',
name="unique_Conv2D_{}".format(3 + 2 * j + 1))
network = max_pool_2d(network, 2)
network = fully_connected(network,
512,
activation='relu',
name="unique_FullyConnected")
network = dropout(network, 0.5)
cur_network = fully_connected(network,
output_dim,
activation='softmax',
name="unique_FullyConnected_1")
cur_network = regression(cur_network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
networks.append(cur_network)
if len(networks) == 1:
return networks[0]
return networks
def ANN(WIDTH, HEIGHT, CHANNELS, LABELS):
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Building the network
network = input_data(shape=[None, WIDTH, HEIGHT, CHANNELS],
data_preprocessing=img_prep,
name='input')
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 128, 3, activation='relu')
network = conv_2d(network, 128, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 256, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = fully_connected(network, 4096, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='relu')
network = dropout(network, 0.5)
# Output layer
merged_layers = fully_connected(network, LABELS, activation='softmax')
network = regression(merged_layers,
optimizer='adam',
learning_rate=0.0005,
loss='categorical_crossentropy',
name='target')
model = tflearn.DNN(network,
tensorboard_verbose=0,
tensorboard_dir='./logs',
best_checkpoint_path='./checkpoints/best/best_val',
max_checkpoints=1)
return model
def train_rec():
X, Y, X_test, Y_test = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
X_test = X_test.reshape([-1, 28, 28, 1])
#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
inputs = input_data(
shape=[None, 28, 28, 1],
data_preprocessing=img_prep,
data_augmentation=img_aug,
name="inputs")
network = conv_2d(inputs, 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 = fully_connected(network, 256, activation='relu')
network = dropout(network, 0.6)
network = fully_connected(network, 10, activation='relu')
network = regression(
network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=3)
global rec_input, rec_network
rec_input, rec_network = inputs, network
model.fit(
X,
Y,
n_epoch=20,
shuffle=True,
validation_set=(X_test, Y_test),
show_metric=True,
batch_size=128,
run_id='mnist')
return model
def load_model(
model_path='/mnt/ARRAY/classifier/model/particle-classifier.tfl'):
'''
Load the trained tensorflow model
Args:
model_path (str) : path to particle-classifier e.g.
'/mnt/ARRAY/classifier/model/particle-classifier.tfl'
Returns:
model (tf model object) : loaded tfl model from load_model()
'''
path, filename = os.path.split(model_path)
header = pd.read_csv(os.path.join(path, 'header.tfl.txt'))
OUTPUTS = len(header.columns)
class_labels = header.columns
tf.reset_default_graph()
# Same network definition as in tfl_tools scripts
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.)
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 = conv_2d(network, 64, 3, activation='relu')
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, 0.75)
network = fully_connected(network, OUTPUTS, activation='softmax')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path=model_path)
model.load(model_path)
return model, class_labels
def load_model():
global model
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.)
# setting up neural network
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, 3, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=1e-3,
loss='categorical_crossentropy')
#TODO: change checkpoint path
model = tflearn.DNN(
network,
checkpoint_path='model_chips_drinks_chocs_canteen_cp.tflearn',
max_checkpoints=3,
tensorboard_verbose=3,
tensorboard_dir='tmp/tflearn_logs/')
model.load('training/model_chips_drinks_chocs_canteen.tflearn')
def _model3():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
network = input_data(shape=[None, inputSize, inputSize, dim],
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, len(yTest[0]), activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
print('Model has been made!!!?')
# Training
model = tflearn.DNN(network, checkpoint_path='model_densenet_cifar10',
max_checkpoints=10, tensorboard_verbose=0,
clip_gradients=0.)
model.load(_path)
pred = model.predict(xTest)
df = pd.DataFrame(pred)
df.to_csv(_path + ".csv")
newList = pred.copy()
newList = convert2(newList)
if _CSV: makeCSV(newList)
pred = convert2(pred)
pred = convert3(pred)
yTest = convert3(yTest)
print(metrics.confusion_matrix(yTest, pred))
print(metrics.classification_report(yTest, pred))
print('Accuracy', accuracy_score(yTest, pred))
print()
if _wrFile: writeTest(pred)
def vgg_graph(X):
tflearn.config.init_training_mode()
tf.reset_default_graph()
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)
network = conv_2d(network, 64, 3, activation='relu')
network = conv_2d(network, 64, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 128, 3, activation='relu')
network = conv_2d(network, 128, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 256, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = conv_2d(network, 512, 3, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = fully_connected(network, 4096, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 2, activation='softmax')
network = regression(network, optimizer='rmsprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
vgg_model = tflearn.DNN(network)
vgg_model.load('model\\vgg\\jun_vgg_cat_dog_final.tflearn')
vgg_result = vgg_model.predict(X)
return vgg_result
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 generate_network(self):
""" Return tflearn cnn network.
"""
print(self.image_size, self.n_epoch, self.batch_size, self.person_ids)
print(type(self.image_size), type(self.n_epoch),
type(self.batch_size), type(self.person_ids))
if not isinstance(self.image_size, list) \
or not isinstance(self.n_epoch, int) \
or not isinstance(self.batch_size, int) \
or not isinstance(self.person_ids, list):
# if self.image_size is None or self.n_epoch is None or \
# self.batch_size is None or self.person_ids is None:
raise ValueError("Insufficient values to generate network.\n"
"Need (n_epoch, int), (batch_size, int),"
"(image_size, list), (person_ids, list).")
# 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_rotation(max_angle=25.)
img_aug.add_random_flip_leftright()
# Convolutional network building
network = input_data(
shape=[None, self.image_size[0], self.image_size[1], 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, self.image_size[0], self.IMAGE_CHANNEL_NUM,
activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, self.image_size[0] * 2,
self.IMAGE_CHANNEL_NUM,
activation='relu')
network = conv_2d(network, self.image_size[0] * 2,
self.IMAGE_CHANNEL_NUM,
activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, self.image_size[0] * 2**4,
activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, self.person_num,
activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
return network
def setup_model(checkpoint_path=None):
"""Sets up a deep belief network for image classification based on the set up described in
:param checkpoint_path: string path describing prefix for model checkpoints
:returns: Deep Neural Network
:rtype: tflearn.DNN
References:
- Machine Learning is Fun! Part 3: Deep Learning and Convolutional Neural Networks
Links:
- https://medium.com/@ageitgey/machine-learning-is-fun-part-3-deep-learning-and-convolutional-neural-networks-f40359318721
"""
# 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.)
# Input is a 32x32 image with 3 color channels (red, green and blue)
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, 2, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
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 _model2():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
net = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
n = 3
j = 64
'''
net = tflearn.conv_2d(net, j, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.residual_block(net, n, j)
net = tflearn.residual_block(net, 1, j*2, downsample=True)
net = tflearn.residual_block(net, n-1, j*2)
net = tflearn.residual_block(net, 1, j*4, downsample=True)
net = tflearn.residual_block(net, n-1, j*4)
net = tflearn.residual_block(net, 1, j*8, downsample=True)
net = tflearn.residual_block(net, n-1, j*8)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
'''
net = tflearn.conv_2d(net, j, 7, strides = 2, regularizer='L2', weight_decay=0.0001)
net = max_pool_2d(net, 2, strides=2)
net = tflearn.residual_block(net, n, j)
net = tflearn.residual_block(net, 1, j*2, downsample=True)
net = tflearn.residual_block(net, n-1, j*2)
net = tflearn.residual_block(net, 1, j*4, downsample=True)
net = tflearn.residual_block(net, n-1, j*4)
net = tflearn.residual_block(net, 1, j*8, downsample=True)
net = tflearn.residual_block(net, n-1, j*8)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
net = tflearn.fully_connected(net, len(Y[0]), activation='softmax')
mom = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=mom,
loss='categorical_crossentropy')
model = tflearn.DNN(net, checkpoint_path='model_resnet_cifar10',
max_checkpoints=10, tensorboard_verbose=3, clip_gradients=0.)
model.fit(X, Y, n_epoch=epochNum, validation_set=(xTest, yTest),snapshot_epoch=False,
snapshot_step=500, show_metric=True, batch_size=batchNum, shuffle=True, run_id= _id + 'artClassification')
if modelStore: model.save(_id + '-model.tflearn')
def _model1():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 32, 3, strides = 4, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, strides = 2, activation='relu')
network = max_pool_2d(network, 2, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, len(yTest[0]), activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy', name='target')
model = tflearn.DNN(network, tensorboard_verbose=3)
model.load(_path)
pred = model.predict(xTest)
df = pd.DataFrame(pred)
df.to_csv(_path + ".csv")
newList = pred.copy()
newList = convert2(newList)
if _CSV: makeCSV(newList)
pred = convert2(pred)
pred = convert3(pred)
yTest = convert3(yTest)
print(metrics.confusion_matrix(yTest, pred))
print(metrics.classification_report(yTest, pred))
print('Accuracy', accuracy_score(yTest, pred))
print()
if _wrFile: writeTest(pred)
def build_model_specific():
### IS ANY OF THIS NECESSARY FOR LIGHT/DARK? IN GENERAL W/ STAIONARY CAMERA?
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
# Specify shape of the data, image prep
network = input_data(shape=[None, 52, 64],
data_preprocessing=img_prep,
data_augmentation=img_aug)
# conv_2d incoming, nb_filter, filter_size
# incoming: Tensor. Incoming 4-D Tensor.
# nb_filter: int. The number of convolutional filters. # WHAT IS THIS?
# filter_size: 'intor list ofints`. Size of filters. # WHAT IS THIS?
network = conv_1d(network, 512, 3, activation='relu')
# (incoming, kernel_size)
# incoming: Tensor. Incoming 4-D Layer.
# kernel_size: 'intor list ofints`. Pooling kernel size.
network = max_pool_1d(network, 2)
network = conv_1d(network, 64, 3, activation='relu')
network = conv_1d(network, 64, 3, activation='relu')
network = max_pool_1d(network, 2)
network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.5)
network = fully_connected(network, 4, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0003)
model = tflearn.DNN(network, tensorboard_verbose=0)
return model
def _model3():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
network = input_data(shape=[None, inputSize, inputSize, dim],
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, len(Y[0]), activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
print('Model has been made!!!?')
# Training
model = tflearn.DNN(network, checkpoint_path='model_densenet_cifar10',
max_checkpoints=10, tensorboard_verbose=0,
clip_gradients=0.)
model.fit(X, Y, n_epoch=epochNum, validation_set=(xTest, yTest),
snapshot_epoch=False, snapshot_step=200,
show_metric=True, batch_size=batchNum, shuffle=True,
run_id='resnext_cifar10')
if modelStore: model.save(_id + '-model.tflearn')
def generate_image_preprocessing(self):
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
return img_prep
def _model4():
# Taken from TFLearn examples and based on Googles Inception. DO NOT RUN!!!!
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
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')
# 3a
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, name='inception_3a_pool')
inception_3a_pool_1_1 = conv_2d(inception_3a_pool, 32, filter_size=1, activation='relu', name='inception_3a_pool_1_1')
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)
# 3b
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')
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')
# 4a
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')
# 4b
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')
# 4c
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')
# 4d
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')
# 4e
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')
# 5a
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')
# 5b
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)
# fc
loss = fully_connected(pool5_7_7, len(yTest[0]), activation='softmax')
network = regression(loss, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
# to train
model = tflearn.DNN(network, checkpoint_path='model_googlenet',
max_checkpoints=1, tensorboard_verbose=2)
model.load(_path)
pred = model.predict(xTest)
df = pd.DataFrame(pred)
df.to_csv(_path + ".csv")
newList = pred.copy()
newList = convert2(newList)
if _CSV: makeCSV(newList)
pred = convert2(pred)
pred = convert3(pred)
yTest = convert3(yTest)
print(metrics.confusion_matrix(yTest, pred))
print(metrics.classification_report(yTest, pred))
print('Accuracy', accuracy_score(yTest, pred))
print()
if _wrFile: writeTest(pred)
from tflearn.layers.estimator import regression from tflearn.data_preprocessing import ImagePreprocessing from tflearn.data_augmentation import ImageAugmentation # Data loading and pre processing from tflearn.datasets import cifar10 (X,Y), (X_test, Y_test) = cifar10.load_data() X, Y = shuffle(X,Y) Y = to_categorical(Y, 10) Y_test = to_categorical(Y_test, 10) # Data preprocessing img_prep = ImagePreprocessing() img_prep.add_featurewise_zero_center() img_prep.add_featurewise_stdnorm() # Data augmentation img_aug = ImageAugmentation() img_aug.add_random_flip_leftright() img_aug.add_random_rotation() # Building the CNN network = input_data(shape=[None, 32, 32, 3], data_preprocessing=img_prep, data_augmentation=img_aug, name='first_layer') network = max_pool_2d(network, 2) # Max pooling layer network = conv_2d(network, 64, 3 , activation='relu') network = conv_2d(network, 64, 3 , activation='relu') # Multiple convolution layers network = max_pool_2d(network, 2) # Max pooling layer network = fully_connected(network, 512, activation='relu') network = dropout(network, 0.5) network = fully_connected(network, 10, activation='softmax') # Layer responsible for prediction
def _model5():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
def block35(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 32, 3, bias=False, activation=None,name='Conv2d_0b_3x3')))
tower_conv2_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 48,3, bias=False, activation=None, name='Conv2d_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 64,3, bias=False, activation=None, name='Conv2d_0c_3x3')))
tower_mixed = merge([tower_conv, tower_conv1_1, tower_conv2_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block17(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv_1_0 = relu(batch_normalization(conv_2d(net, 128, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv_1_1 = relu(batch_normalization(conv_2d(tower_conv_1_0, 160,[1,7], bias=False, activation=None,name='Conv2d_0b_1x7')))
tower_conv_1_2 = relu(batch_normalization(conv_2d(tower_conv_1_1, 192, [7,1], bias=False, activation=None,name='Conv2d_0c_7x1')))
tower_mixed = merge([tower_conv,tower_conv_1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block8(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 224, [1,3], bias=False, activation=None, name='Conv2d_0b_1x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 256, [3,1], bias=False, name='Conv2d_0c_3x1')))
tower_mixed = merge([tower_conv,tower_conv1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
num_classes = len(yTest[0])
dropout_keep_prob = 0.8
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
conv1a_3_3 = relu(batch_normalization(conv_2d(network, 32, 3, strides=2, bias=False, padding='VALID',activation=None,name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(batch_normalization(conv_2d(conv1a_3_3, 32, 3, bias=False, padding='VALID',activation=None, name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(batch_normalization(conv_2d(conv2a_3_3, 64, 3, bias=False, activation=None, name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3, 3, strides=2, padding='VALID', name='MaxPool_3a_3x3')
conv3b_1_1 = relu(batch_normalization(conv_2d(maxpool3a_3_3, 80, 1, bias=False, padding='VALID',activation=None, name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(batch_normalization(conv_2d(conv3b_1_1, 192, 3, bias=False, padding='VALID',activation=None, name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3, 3, strides=2, padding='VALID', name='MaxPool_5a_3x3')
tower_conv = relu(batch_normalization(conv_2d(maxpool5a_3_3, 96, 1, bias=False, activation=None, name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 48, 1, bias=False, activation=None, name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 64, 5, bias=False, activation=None, name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 64, 1, bias=False, activation=None, name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 96, 3, bias=False, activation=None, name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 96, 3, bias=False, activation=None,name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3, 3, strides=1, padding='same', name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(batch_normalization(conv_2d(tower_pool3_0, 64, 1, bias=False, activation=None,name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge([tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1], mode='concat', axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 3, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 3, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,3, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,3, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 1, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,1, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,1, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 1, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID', name='MaxPool_1a_3x3')
####
net = merge([tower_conv0_1, tower_conv1_1,tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
net = relu(batch_normalization(conv_2d(net, 1536, 1, bias=False, activation=None, name='Conv2d_7b_1x1')))
net = avg_pool_2d(net, net.get_shape().as_list()[1:3],strides=2, padding='VALID', name='AvgPool_1a_8x8')
net = flatten(net)
net = dropout(net, dropout_keep_prob)
loss = fully_connected(net, num_classes,activation='softmax')
network = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = tflearn.DNN(network, checkpoint_path='inception_resnet_v2',
max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir="./tflearn_logs/")
model.load(_path)
pred = model.predict(xTest)
df = pd.DataFrame(pred)
df.to_csv(_path + ".csv")
newList = pred.copy()
newList = convert2(newList)
if _CSV: makeCSV(newList)
pred = convert2(pred)
pred = convert3(pred)
yTest = convert3(yTest)
print(metrics.confusion_matrix(yTest, pred))
print(metrics.classification_report(yTest, pred))
print('Accuracy', accuracy_score(yTest, pred))
print()
if _wrFile: writeTest(pred)
def _model4():
# Taken from TFLearn examples and based on Googles Inception. DO NOT RUN!!!!
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
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')
# 3a
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, name='inception_3a_pool')
inception_3a_pool_1_1 = conv_2d(inception_3a_pool, 32, filter_size=1, activation='relu', name='inception_3a_pool_1_1')
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)
# 3b
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')
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')
# 4a
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')
# 4b
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')
# 4c
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')
# 4d
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')
# 4e
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')
# 5a
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')
# 5b
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)
# fc
loss = fully_connected(pool5_7_7, len(Y[0]), activation='softmax')
network = regression(loss, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
# to train
model = tflearn.DNN(network, checkpoint_path='model_googlenet',
max_checkpoints=1, tensorboard_verbose=2)
model.fit(X, Y, n_epoch=epochNum, validation_set=(xTest, yTest), shuffle=True,
show_metric=True, batch_size=batchNum, snapshot_step=200,
snapshot_epoch=False, run_id='googlenet_oxflowers17')
if modelStore: model.save(_id + '-model.tflearn')
def _model5():
global yTest, img_aug
tf.reset_default_graph()
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
def block35(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 32, 3, bias=False, activation=None,name='Conv2d_0b_3x3')))
tower_conv2_0 = relu(batch_normalization(conv_2d(net, 32, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 48,3, bias=False, activation=None, name='Conv2d_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 64,3, bias=False, activation=None, name='Conv2d_0c_3x3')))
tower_mixed = merge([tower_conv, tower_conv1_1, tower_conv2_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block17(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv_1_0 = relu(batch_normalization(conv_2d(net, 128, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv_1_1 = relu(batch_normalization(conv_2d(tower_conv_1_0, 160,[1,7], bias=False, activation=None,name='Conv2d_0b_1x7')))
tower_conv_1_2 = relu(batch_normalization(conv_2d(tower_conv_1_1, 192, [7,1], bias=False, activation=None,name='Conv2d_0c_7x1')))
tower_mixed = merge([tower_conv,tower_conv_1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
def block8(net, scale=1.0, activation="relu"):
tower_conv = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 192, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 224, [1,3], bias=False, activation=None, name='Conv2d_0b_1x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 256, [3,1], bias=False, name='Conv2d_0c_3x1')))
tower_mixed = merge([tower_conv,tower_conv1_2], mode='concat', axis=3)
tower_out = relu(batch_normalization(conv_2d(tower_mixed, net.get_shape()[3], 1, bias=False, activation=None, name='Conv2d_1x1')))
net += scale * tower_out
if activation:
if isinstance(activation, str):
net = activations.get(activation)(net)
elif hasattr(activation, '__call__'):
net = activation(net)
else:
raise ValueError("Invalid Activation.")
return net
num_classes = len(Y[0])
dropout_keep_prob = 0.8
network = input_data(shape=[None, inputSize, inputSize, dim],
name='input',
data_preprocessing=img_prep,
data_augmentation=img_aug)
conv1a_3_3 = relu(batch_normalization(conv_2d(network, 32, 3, strides=2, bias=False, padding='VALID',activation=None,name='Conv2d_1a_3x3')))
conv2a_3_3 = relu(batch_normalization(conv_2d(conv1a_3_3, 32, 3, bias=False, padding='VALID',activation=None, name='Conv2d_2a_3x3')))
conv2b_3_3 = relu(batch_normalization(conv_2d(conv2a_3_3, 64, 3, bias=False, activation=None, name='Conv2d_2b_3x3')))
maxpool3a_3_3 = max_pool_2d(conv2b_3_3, 3, strides=2, padding='VALID', name='MaxPool_3a_3x3')
conv3b_1_1 = relu(batch_normalization(conv_2d(maxpool3a_3_3, 80, 1, bias=False, padding='VALID',activation=None, name='Conv2d_3b_1x1')))
conv4a_3_3 = relu(batch_normalization(conv_2d(conv3b_1_1, 192, 3, bias=False, padding='VALID',activation=None, name='Conv2d_4a_3x3')))
maxpool5a_3_3 = max_pool_2d(conv4a_3_3, 3, strides=2, padding='VALID', name='MaxPool_5a_3x3')
tower_conv = relu(batch_normalization(conv_2d(maxpool5a_3_3, 96, 1, bias=False, activation=None, name='Conv2d_5b_b0_1x1')))
tower_conv1_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 48, 1, bias=False, activation=None, name='Conv2d_5b_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 64, 5, bias=False, activation=None, name='Conv2d_5b_b1_0b_5x5')))
tower_conv2_0 = relu(batch_normalization(conv_2d(maxpool5a_3_3, 64, 1, bias=False, activation=None, name='Conv2d_5b_b2_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2_0, 96, 3, bias=False, activation=None, name='Conv2d_5b_b2_0b_3x3')))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 96, 3, bias=False, activation=None,name='Conv2d_5b_b2_0c_3x3')))
tower_pool3_0 = avg_pool_2d(maxpool5a_3_3, 3, strides=1, padding='same', name='AvgPool_5b_b3_0a_3x3')
tower_conv3_1 = relu(batch_normalization(conv_2d(tower_pool3_0, 64, 1, bias=False, activation=None,name='Conv2d_5b_b3_0b_1x1')))
tower_5b_out = merge([tower_conv, tower_conv1_1, tower_conv2_2, tower_conv3_1], mode='concat', axis=3)
net = repeat(tower_5b_out, 10, block35, scale=0.17)
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 3, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 3, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 3, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,3, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,3, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 3, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 3, strides=2, padding='VALID', name='MaxPool_1a_3x3')
'''
tower_conv = relu(batch_normalization(conv_2d(net, 384, 1, bias=False, strides=2,activation=None, padding='VALID', name='Conv2d_6a_b0_0a_3x3')))
tower_conv1_0 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1_0, 256, 1, bias=False, activation=None, name='Conv2d_6a_b1_0b_3x3')))
tower_conv1_2 = relu(batch_normalization(conv_2d(tower_conv1_1, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_6a_b1_0c_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID',name='MaxPool_1a_3x3')
net = merge([tower_conv, tower_conv1_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 20, block17, scale=0.1)
tower_conv = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, activation=None, name='Conv2d_0a_1x1')))
tower_conv0_1 = relu(batch_normalization(conv_2d(tower_conv, 384, 1, bias=False, strides=2, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1 = relu(batch_normalization(conv_2d(net, 256, 1, bias=False, padding='VALID', activation=None,name='Conv2d_0a_1x1')))
tower_conv1_1 = relu(batch_normalization(conv_2d(tower_conv1,288,1, bias=False, strides=2, padding='VALID',activation=None, name='COnv2d_1a_3x3')))
tower_conv2 = relu(batch_normalization(conv_2d(net, 256,1, bias=False, activation=None,name='Conv2d_0a_1x1')))
tower_conv2_1 = relu(batch_normalization(conv_2d(tower_conv2, 288,1, bias=False, name='Conv2d_0b_3x3',activation=None)))
tower_conv2_2 = relu(batch_normalization(conv_2d(tower_conv2_1, 320, 1, bias=False, strides=2, padding='VALID',activation=None, name='Conv2d_1a_3x3')))
tower_pool = max_pool_2d(net, 1, strides=2, padding='VALID', name='MaxPool_1a_3x3')
####
net = merge([tower_conv0_1, tower_conv1_1,tower_conv2_2, tower_pool], mode='concat', axis=3)
net = repeat(net, 9, block8, scale=0.2)
net = block8(net, activation=None)
net = relu(batch_normalization(conv_2d(net, 1536, 1, bias=False, activation=None, name='Conv2d_7b_1x1')))
net = avg_pool_2d(net, net.get_shape().as_list()[1:3],strides=2, padding='VALID', name='AvgPool_1a_8x8')
net = flatten(net)
net = dropout(net, dropout_keep_prob)
loss = fully_connected(net, num_classes,activation='softmax')
network = tflearn.regression(loss, optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = tflearn.DNN(network, checkpoint_path='inception_resnet_v2',
max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir="./tflearn_logs/")
model.fit(X, Y, n_epoch=epochNum, validation_set=(xTest, yTest), shuffle=True,
show_metric=True, batch_size=batchNum, snapshot_step=2000,
snapshot_epoch=False, run_id='inception_resnet_v2_oxflowers17')
if modelStore: model.save(_id + '-model.tflearn')
