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 _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 _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 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 _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 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')
if (comm_multi_label_scenario == 1):
XTrain, YTrain, num_output_classes = ssld.load_multi_label_data(
comm_train_text_file_ML,
comm_root_image_path_ML,
(cnn_image_shape_before_crop[0], cnn_image_shape_before_crop[1]),
normalize=True,
grayscale=False)
XVal, YVal, num_output_classes = ssld.load_multi_label_data(
comm_val_text_file_ML,
comm_root_image_path_ML,
(cnn_image_shape_before_crop[0], cnn_image_shape_before_crop[1]),
normalize=True,
grayscale=False)
# Image Preprocessing Methods Instantiation
cnn_img_prep = ImagePreprocessing()
if (cnn_compute_mean_std == 1):
cnn_img_prep.add_featurewise_zero_center(
) # Zero Center (With mean computed over the whole dataset)
cnn_img_prep.add_featurewise_stdnorm(
) # STD Normalization (With std computed over the whole dataset)
if (cnn_compute_mean_std == 0):
cnn_img_prep.add_featurewise_zero_center(per_channel=True,
mean=cnn_mean_vector_precomputed)
cnn_img_prep.add_featurewise_stdnorm(per_channel=True,
std=cnn_std_vector_precomputed)
cnn_img_aug = tflearn.ImageAugmentation() # Real-time data augmentation
cnn_img_aug.add_random_flip_leftright() # Random flip an image
cnn_img_aug.add_random_crop([cnn_image_shape[0], cnn_image_shape[1]])
files_list = "/path/to/your/file/with/images"
from tflearn.data_utils import image_preloader
X, Y = image_preloader(files_list, image_shape=(224, 224), mode='file',
categorical_labels=True, normalize=False,
files_extension=['.jpg', '.png'], filter_channel=True)
# or use the mode 'floder'
# X, Y = image_preloader(data_dir, image_shape=(224, 224), mode='folder',
# categorical_labels=True, normalize=True,
# files_extension=['.jpg', '.png'], filter_channel=True)
num_classes = 10 # num of your dataset
# VGG preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center(mean=[123.68, 116.779, 103.939],
per_channel=True)
# VGG Network
x = tflearn.input_data(shape=[None, 224, 224, 3], name='input',
data_preprocessing=img_prep)
softmax = vgg16(x, num_classes)
regression = tflearn.regression(softmax, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001, restore=False)
model = tflearn.DNN(regression, checkpoint_path='vgg-finetuning',
max_checkpoints=3, tensorboard_verbose=2,
tensorboard_dir="./logs")
model_file = os.path.join(model_path, "vgg16.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(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)
index = int(tmp[1])
label = np.zeros(num_clss)
label[index] = 1
labels.append(label)
if save:
pickle.dump((images, labels), open(save_path, 'wb'))
return images, labels
def load_from_pkl(dataset_file):
X, Y = pickle.load(open(dataset_file, 'rb'))
return X, Y
# Make sure the data is normalized
img_prep = ImagePreprocessing()
# img_prep.add_featurewise_zero_center(31.83)
# img_prep.add_featurewise_stdnorm(50.96)
# 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_crop((227, 227), 20)
img_aug.add_random_rotation(max_angle=180.)
def create_alexnet(num_classes):
# Building 'AlexNet'
network = input_data(shape=[None, 227, 227, 3],
data_preprocessing=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(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')
print(Y.shape)
#Reshaping the Numpy Arrays
X = X.reshape([-1, 256, 256, 3])
X_test = X_test.reshape([-1, 256, 256, 3])
Y = to_categorical(Y, 3)
Y_test = to_categorical(Y_test, 3)
print("Starting Data Manipulation...")
# Shuffle the data
print("Shuffling the Data...")
# Shuffle the data
X, Y = shuffle(X, Y)
# Make sure the data is normalized
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping, rotating and blurring the
# images on our data set.
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
img_aug.add_random_blur(sigma_max=3.)
# Define our network architecture:
# Input is a 32x32 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, 256, 256, 3],
data_preprocessing=img_prep,
X, Y = image_preloader(files_list,
image_shape=(224, 224),
mode='file',
categorical_labels=True,
normalize=False,
files_extension=['.jpg', '.png'],
filter_channel=True)
# or use the mode 'floder'
# X, Y = image_preloader(data_dir, image_shape=(224, 224), mode='folder',
# categorical_labels=True, normalize=True,
# files_extension=['.jpg', '.png'], filter_channel=True)
num_classes = 10 # num of your dataset
# VGG preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center(mean=[123.68, 116.779, 103.939],
per_channel=True)
# VGG Network
x = tflearn.input_data(shape=[None, 224, 224, 3],
name='input',
data_preprocessing=img_prep)
softmax = vgg16(x, num_classes)
regression = tflearn.regression(softmax,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001,
restore=False)
model = tflearn.DNN(regression,
checkpoint_path='vgg-finetuning',
from tflearn.data_augmentation import ImageAugmentation
from tflearn.data_utils import image_preloader
# Data Loading and Categorization
runbook = 'data/mowmowSanity.csv'
X, Y = image_preloader(runbook,
image_shape=(128, 128),
mode='file',
categorical_labels=False,
normalize=False)
Y = to_categorical(Y, 4)
print(Y)
print("-- Runbook Import Complete.")
# Real-time Data Preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center(mean=110.53345696347691)
img_prep.add_featurewise_stdnorm(std=30.956539195568315)
print("-- Data Preprocessing Complete.")
# Real-time Data Augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
print("-- Data Augmentation Complete.")
# Convolutional Network
network = input_data(shape=[None, 128, 128, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network,
y_test = y_test.reshape(-1) # In[16]: y_train_ohc = pd.get_dummies(y_train) y_test_ohc = pd.get_dummies(y_test) # In[17]: # shuffling the data X_train, y_train = shuffle(X_train, y_train) # In[18]: # normalizing img_pre = ImagePreprocessing() img_pre.add_featurewise_zero_center(33.3184) img_pre.add_featurewise_stdnorm(78.56748998339795) # In[19]: # image augmentation img_aug = ImageAugmentation() img_aug.add_random_flip_leftright() img_aug.add_random_rotation(max_angle=25.) img_aug.add_random_blur(sigma_max=3.) # ## Network Architecture # In[20]:
def network1(train, train_amount):
global model
# region SPLIT DATA FOR TRAIN/VALIDATION
train_amount = int(train_amount * 5.5 / 6)
x_train = np.array([i[0] for i in train[:train_amount]
]).reshape(-1, s.IMG_SIZE, s.IMG_SIZE, 1)
x_train = x_train / 255.0
y_train = [i[1] for i in train[:train_amount]]
x_validation = np.array([i[0] for i in train[train_amount:]
]).reshape(-1, s.IMG_SIZE, s.IMG_SIZE, 1)
x_validation = x_validation / 255.0
y_validation = [i[1] for i in train[train_amount:]]
# endregion
# region NETWORK
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center(mean=[0.4735053442384178])
network = input_data(shape=[None, s.IMG_SIZE, s.IMG_SIZE, 1],
name='input',
data_preprocessing=img_prep)
network = conv_2d(network, 32, 3, activation='relu', scope='conv1_1')
network = conv_2d(network, 64, 3, activation='relu', scope='conv1_2')
network = max_pool_2d(network, 2, strides=2, name='maxpool_1')
network = conv_2d(network, 128, 3, activation='relu', scope='conv2_1')
network = max_pool_2d(network, 2, strides=2, name='maxpool_2')
network = conv_2d(network, 128, 3, activation='relu', scope='conv3_1')
network = max_pool_2d(network, 2, strides=2, name='maxpool_3')
network = conv_2d(network, 256, 3, activation='relu', scope='conv4_1')
network = max_pool_2d(network, 2, strides=2, name='maxpool_4')
network = fully_connected(network, 1024, activation='relu', scope='fc5')
network = dropout(network, 0.5, name='dropout_1')
network = fully_connected(network, 1024, activation='relu', scope='fc6')
network = dropout(network, 0.5, name='dropout_2')
network = fully_connected(network,
s.len_animals,
activation='softmax',
scope='fc7')
network = regression(network,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=s.LR,
name='targets')
model = tflearn.DNN(network, tensorboard_verbose=0, tensorboard_dir='log')
# endregion
if os.path.exists('{}.meta'.format(s.MODEL_NAME)):
model.load(s.MODEL_NAME)
print('Model loaded')
# region TRAIN1
model.fit(x_train,
y_train,
n_epoch=12,
validation_set=({
'input': x_validation
}, {
'targets': y_validation
}),
shuffle=True,
snapshot_epoch=True,
show_metric=True,
batch_size=100,
run_id=s.MODEL_NAME)
# endregion
# region SAVE
model.save(s.MODEL_NAME)
print('Network trained and saved as {0}'.format(s.MODEL_NAME))
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()
# 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, 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('current_model/model_resnet_emotion-42000')
face_cascade = cv2.CascadeClassifier(
'haarcascade_frontalface_default.xml')
cap = cv2.VideoCapture(0)
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.process_image(roi_gray, img)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release()
cv2.destroyAllWindows()
def color():
###################################
### Import picture files
###################################
files_path = "./img_align_celeba/"
glasses_files_path = os.path.join(files_path, '*.jpg')
glasses_files = sorted(glob(glasses_files_path))
n_files = len(glasses_files)
#print(n_files)
#size_image1 =178
#size_image2=218
size_image1=27
size_image2=33
allX = np.zeros((n_files, size_image1, size_image2, 3), dtype='float32')
ally = np.zeros(n_files)
count = 0
for f in glasses_files:
try:
img = io.imread(f)
new_img = skimage.transform.resize(img, (27, 33, 3))
allX[count] = np.array(new_img)
ally[count] = 0
count += 1
except:
continue
attribute=[]
g = open('./list_attr_celeba.txt', 'r')
text = g.readlines()
text = np.array(text)
attr2idx = dict()
for i, attr in enumerate(text[1].split()):
attr2idx[attr] = i
attr_index = attr2idx['Eyeglasses']#'Eyeglasses'
for i in text[2:]:
value = i.split()
attribute.append(value[attr_index + 1]) #First index is image name
attribute = np.array(attribute,dtype= np.float32)
#print("Converting Label.................")
for i in range(0,len(attribute)):
if (attribute[i] == 1):
ally[i]=1
else:
ally[i]=0
ally = np.array(ally)
########break up data into training, validation, and test sets
train_limit = int(math.floor(0.8 * len(allX)))
validate_limit = int(math.floor(0.1*len(allX)))
#print (train_limit, validate_limit)
X = allX[0:train_limit,:,]
X_validation = allX[(train_limit+1):(train_limit+validate_limit),:,]
X_test = allX[(train_limit+validate_limit+1):,:,]
Y = ally[0:train_limit]
Y_validation = ally[(train_limit+1):(train_limit+validate_limit)]
Y_test = ally[(train_limit+validate_limit+1):]
# encode the Ys
Y = to_categorical(Y, 2)
Y_test = to_categorical(Y_test, 2)
Y_validation = to_categorical(Y_validation, 2)
#take a subset of training dataset to find parameters
x_sm = int(math.floor(0.8 * len(allX))*0.5)
print (x_sm)
X_sm = allX[0:x_sm,:,]
Y_sm = ally[0:x_sm]
Y_sm=to_categorical(Y_sm, 2)
print (X.shape, Y.shape, allX.shape, ally.shape, X_sm.shape)
###################################
# Image transformations
###################################
# normalisation of images
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Create extra synthetic training data by flipping & rotating images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
###################################
# Define network architecture
###################################
# Input is a 27x33 image with 3 color channels (red, green and blue)
network = input_data(shape=[None, 27, 33, 3])
#,data_preprocessing=img_prep,
#data_augmentation=img_aug)
# 1: Convolution layer with 32 filters, each 3x3x3
conv_1 = conv_2d(network, 32, 3, activation='relu', name='conv_1')
# 2: Max pooling layer
network = max_pool_2d(conv_1, 2)
# 3: Convolution layer with 64 filters
conv_2 = conv_2d(network, 64, 3, activation='relu', name='conv_2')
#4: Convolution layer with 64 filters
conv_3 = conv_2d(conv_2, 64, 3, activation='relu', name='conv_3')
# 5: Max pooling layer
network = max_pool_2d(conv_3, 2)
# 6: Fully-connected 512 node layer
network = fully_connected(network, 1024, activation='relu')
# 7: Dropout layer to combat overfitting
network = dropout(network, 0.5)
# 8: Fully-connected layer with two outputs
network = fully_connected(network, 2, activation='softmax')
# Configure how the network will be trained
acc = Accuracy(name="Accuracy")
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001, metric=acc)
# Wrap the network in a model object
model = tflearn.DNN(network, checkpoint_path='model_glasses_6.tflearn', max_checkpoints = 3,
tensorboard_verbose = 3, tensorboard_dir='tmp/tflearn_logs/')
###################################
# Train model for 1000 epochs
###################################
model.fit(X_sm, Y_sm, validation_set=(X_validation, Y_validation), batch_size=50,
n_epoch=1000, run_id='model_glasses_6', show_metric=True)
model.save('model_glasses_6_final.tflearn')
# Evaluate model
score = model.evaluate(X_test, Y_test)
print('Test accuarcy: %0.4f%%' % (score[0] * 100))
def main(_):
dirname = os.path.join(FLAGS.buckets, "")
(X, Y), (X_test, Y_test) = load_data(dirname)
print("load data done")
X, Y = shuffle(X, Y)
Y = to_categorical(Y, 10)
Y_test = to_categorical(Y_test, 10)
# Real-time data preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
# Real-time data augmentation
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.)
# Convolutional network building
network = input_data(shape=[None, 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=100, shuffle=True, validation_set=(X_test, Y_test),
# show_metric=True, batch_size=96, run_id='cifar10_cnn')
model_path = os.path.join(FLAGS.checkpointDir, "model.tfl")
print(model_path)
model.load(model_path)
# predict_pic = os.path.join(FLAGS.buckets, "bird_mount_bluebird.jpg")
# file_paths = tf.train.match_filenames_once(predict_pic)
# input_file_queue = tf.train.string_input_producer(file_paths)
# reader = tf.WholeFileReader()
# file_path, raw_data = reader.read(input_file_queue)
# img = tf.image.decode_jpeg(raw_data, 3)
# img = tf.image.resize_images(img, [32, 32])
# prediction = model.predict([img])
# print (prediction[0])
predict_pic = os.path.join(FLAGS.buckets, "bird_bullocks_oriole.jpg")
img_obj = file_io.read_file_to_string(predict_pic)
file_io.write_string_to_file("bird_bullocks_oriole.jpg", img_obj)
img = scipy.ndimage.imread("bird_bullocks_oriole.jpg", mode="RGB")
# Scale it to 32x32
img = scipy.misc.imresize(img, (32, 32), interp="bicubic").astype(np.float32, casting='unsafe')
# Predict
prediction = model.predict([img])
print (prediction[0])
print (prediction[0])
#print (prediction[0].index(max(prediction[0])))
num=['airplane','automobile','bird','cat','deer','dog','frog','horse','ship','truck']
print ("This is a %s"%(num[prediction[0].index(max(prediction[0]))]))
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')
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.core import input_data, dropout, fully_connected from tflearn.layers.conv import conv_2d, max_pool_2d 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')
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
