def build_network(self):
# Building 'AlexNet'
# https://github.com/tflearn/tflearn/blob/master/examples/images/alexnet.py
# https://github.com/DT42/squeezenet_demo
# https://github.com/yhenon/pysqueezenet/blob/master/squeezenet.py
print('[+] Building CNN')
self.network = input_data(shape = [None, SIZE_FACE, SIZE_FACE, 1])
self.network = conv_2d(self.network, 96, 11, strides = 4, activation = 'relu')
self.network = max_pool_2d(self.network, 3, strides = 2)
self.network = local_response_normalization(self.network)
self.network = conv_2d(self.network, 256, 5, activation = 'relu')
self.network = max_pool_2d(self.network, 3, strides = 2)
self.network = local_response_normalization(self.network)
self.network = conv_2d(self.network, 256, 3, activation = 'relu')
self.network = max_pool_2d(self.network, 3, strides = 2)
self.network = local_response_normalization(self.network)
self.network = fully_connected(self.network, 1024, activation = 'tanh')
self.network = dropout(self.network, 0.5)
self.network = fully_connected(self.network, 1024, activation = 'tanh')
self.network = dropout(self.network, 0.5)
self.network = fully_connected(self.network, len(EMOTIONS), activation = 'softmax')
self.network = regression(self.network,
optimizer = 'momentum',
loss = 'categorical_crossentropy')
self.model = tflearn.DNN(
self.network,
checkpoint_path = SAVE_DIRECTORY + '/alexnet_mood_recognition',
max_checkpoints = 1,
tensorboard_verbose = 2
)
self.load_model()
def createModel(nbClasses,imageSize):
print("[+] Creating model...")
convnet = input_data(shape=[None, imageSize, imageSize, 1], name='input')
convnet = conv_2d(convnet, 64, 2, activation='elu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 128, 2, activation='elu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 256, 2, activation='elu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 512, 2, activation='elu', weights_init="Xavier")
convnet = max_pool_2d(convnet, 2)
convnet = fully_connected(convnet, 1024, activation='elu')
convnet = dropout(convnet, 0.5)
convnet = fully_connected(convnet, nbClasses, activation='softmax')
convnet = regression(convnet, optimizer='rmsprop', loss='categorical_crossentropy')
model = tflearn.DNN(convnet)
print(" Model created! ✅")
return model
def cnn():
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28, 1])
testX = testX.reshape([-1, 28, 28, 1])
# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 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, 10, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.01,
loss='categorical_crossentropy', name='target')
# Training
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit({'input': X}, {'target': Y}, n_epoch=20,
validation_set=({'input': testX}, {'target': testY}),
snapshot_step=100, show_metric=True, run_id='cnn_demo')
def train_nmf_network(mfcc_array, sdr_array, n_epochs, take):
"""
:param mfcc_array:
:param sdr_array:
:param n_epochs:
:param take:
:return:
"""
with tf.Graph().as_default():
network = input_data(shape=[None, 13, 100, 1])
network = conv_2d(network, 32, [5, 5], activation="relu", regularizer="L2")
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, [5, 5], activation="relu", regularizer="L2")
network = max_pool_2d(network, 2)
network = fully_connected(network, 128, activation="relu")
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation="relu")
network = dropout(network, 0.8)
network = fully_connected(network, 1, activation="linear")
regress = tflearn.regression(network, optimizer="rmsprop", loss="mean_square", learning_rate=0.001)
# Training
model = tflearn.DNN(regress) # , session=sess)
model.fit(
mfcc_array,
sdr_array,
n_epoch=n_epochs,
snapshot_step=1000,
show_metric=True,
run_id="repet_choice_{0}_epochs_take_{1}".format(n_epochs, take),
)
return model
def alexnet():
X, Y = oxflower17.load_data(one_hot=True, resize_pics=(227, 227))
# Building 'AlexNet'
network = input_data(shape=[None, 227, 227, 3])
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, 17, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
# Training
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
max_checkpoints=1, tensorboard_verbose=2)
model.fit(X, Y, n_epoch=1000, validation_set=0.1, shuffle=True,
show_metric=True, batch_size=64, snapshot_step=200,
snapshot_epoch=False, run_id='alexnet')
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 alexnet(width, height, lr, output=3):
network = input_data(shape=[None, width, height, 1], name='input')
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, output, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=lr, name='targets')
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
max_checkpoints=1, tensorboard_verbose=0, tensorboard_dir='log')
return model
def do_cnn_doc2vec_2d(trainX, testX, trainY, testY):
print "CNN and doc2vec 2d"
trainX = trainX.reshape([-1, max_features, max_document_length, 1])
testX = testX.reshape([-1, max_features, max_document_length, 1])
# Building convolutional network
network = input_data(shape=[None, max_features, max_document_length, 1], name='input')
network = conv_2d(network, 16, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 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, 10, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.01,
loss='categorical_crossentropy', name='target')
# Training
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit({'input': trainX}, {'target': trainY}, n_epoch=20,
validation_set=({'input': testX}, {'target': testY}),
snapshot_step=100, show_metric=True, run_id='review')
def model_for_type(neural_net_type, tile_size, on_band_count):
"""The neural_net_type can be: one_layer_relu,
one_layer_relu_conv,
two_layer_relu_conv."""
network = tflearn.input_data(shape=[None, tile_size, tile_size, on_band_count])
# NN architectures mirror ch. 3 of www.cs.toronto.edu/~vmnih/docs/Mnih_Volodymyr_PhD_Thesis.pdf
if neural_net_type == "one_layer_relu":
network = tflearn.fully_connected(network, 64, activation="relu")
elif neural_net_type == "one_layer_relu_conv":
network = conv_2d(network, 64, 12, strides=4, activation="relu")
network = max_pool_2d(network, 3)
elif neural_net_type == "two_layer_relu_conv":
network = conv_2d(network, 64, 12, strides=4, activation="relu")
network = max_pool_2d(network, 3)
network = conv_2d(network, 128, 4, activation="relu")
else:
print("ERROR: exiting, unknown layer type for neural net")
# classify as road or not road
softmax = tflearn.fully_connected(network, 2, activation="softmax")
# hyperparameters based on www.cs.toronto.edu/~vmnih/docs/Mnih_Volodymyr_PhD_Thesis.pdf
momentum = tflearn.optimizers.Momentum(learning_rate=0.005, momentum=0.9, lr_decay=0.0002, name="Momentum")
net = tflearn.regression(softmax, optimizer=momentum, loss="categorical_crossentropy")
return tflearn.DNN(net, tensorboard_verbose=0)
def main():
pickle_folder = '../pickles_rolloff'
pickle_folders_to_load = [f for f in os.listdir(pickle_folder) if os.path.isdir(join(pickle_folder, f))]
pickle_folders_to_load = sorted(pickle_folders_to_load)
# pickle parameters
fg_or_bg = 'background'
sdr_type = 'sdr'
feature = 'sim_mat'
beat_spec_len = 432
# training params
n_classes = 16
training_percent = 0.85
testing_percent = 0.15
validation_percent = 0.00
# set up training, testing, & validation partitions
print('Loading sim_mat and sdrs')
sim_mat_array, sdr_array = get_generated_data(feature, fg_or_bg, sdr_type)
print('sim_mat and sdrs loaded')
print('splitting and grooming data')
train, test, validate = split_into_sets(len(pickle_folders_to_load), training_percent,
testing_percent, validation_percent)
trainX = np.expand_dims([sim_mat_array[i] for i in train], -1)
trainY = np.expand_dims([sdr_array[i] for i in train], -1)
testX = np.expand_dims([sim_mat_array[i] for i in test], -1)
testY = np.array([sdr_array[i] for i in test])
print('setting up CNN')
# Building convolutional network
network = input_data(shape=[None, beat_spec_len, beat_spec_len, 1])
network = conv_2d(network, 32, 10, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, 20, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
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, 1, activation='linear')
regress = tflearn.regression(network, optimizer='sgd', loss='mean_square', learning_rate=0.01)
print('running CNN')
# Training
model = tflearn.DNN(regress, tensorboard_verbose=1)
model.fit(trainX, trainY, n_epoch=10,
snapshot_step=1000, show_metric=True, run_id='{} classes'.format(n_classes - 1))
predicted = np.array(model.predict(testX))[:,0]
print('plotting')
plot(testY, predicted)
def make_core_network(network):
network = tflearn.reshape(network, [-1, 28, 28, 1], name="reshape")
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 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, 10, activation='softmax')
return network
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 _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 build_network(image_size, batch_size=None, n_channels=3):
network = input_data(shape=[batch_size, image_size[0], image_size[1], n_channels],
data_preprocessing=img_prep,
data_augmentation=img_aug)
network = conv_2d(network, 16, 3, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 32, 3, activation='relu')
network = max_pool_2d(network, 2)
network = fully_connected(network, num_classes, activation='softmax')
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.0001)
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 main():
"""
:return:
"""
pickle_folder = '../NMF/mfcc_pickles'
pickle_folders_to_load = [f for f in os.listdir(pickle_folder) if os.path.isdir(join(pickle_folder, f))]
fg_or_bg = 'background'
sdr_type = 'sdr'
feature = 'mfcc_clusters'
beat_spec_len = 432
n_epochs = 200
take = 1
# set up training, testing, & validation partitions
mfcc_array, sdr_array = load_mfcc_and_sdrs(pickle_folders_to_load, pickle_folder,
feature, fg_or_bg, sdr_type)
mfcc_array = np.expand_dims(mfcc_array, -1)
sdr_array = np.expand_dims(sdr_array, -1)
# Building convolutional network
network = input_data(shape=[None, 13, 100, 1])
network = conv_2d(network, 32, [5, 5], activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, [5, 5], activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='relu')
network = dropout(network, 0.8)
network = fully_connected(network, 1, activation='linear')
regress = tflearn.regression(network, optimizer='rmsprop', loss='mean_square', learning_rate=0.001)
start = time.time()
# Training
model = tflearn.DNN(regress) # , session=sess)
model.fit(mfcc_array, sdr_array, n_epoch=n_epochs,
snapshot_step=1000, show_metric=True,
run_id='repet_save_{0}_epochs_take_{1}'.format(n_epochs, take))
elapsed = (time.time() - start)
print('Finished training after ' + elapsed + 'seconds. Saving...')
model_output_folder = 'network_outputs/'
model_output_file = join(model_output_folder, 'nmf_save_{0}_epochs_take_{1}'.format(n_epochs, take))
model.save(model_output_file)
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 convolutional_neural_network(width=5, height=6):
"""Create the neural network model.
Args:
width: Width of the pseudo image
height: Height of the pseudo image
Returns:
convnet: Output
"""
# Initialize key variables
conv1_filter_count = 32
conv2_filter_count = 64
fc_units = 1024
image_height = height
image_width = width
filter_size = 2
pooling_kernel_size = 2
keep_probability = 0.6
fully_connected_units = 10
# Create the convolutional network stuff
convnet = input_data(
shape=[None, image_width, image_height, 1], name='input')
convnet = conv_2d(
convnet, conv1_filter_count, filter_size, activation='relu')
convnet = max_pool_2d(convnet, pooling_kernel_size)
convnet = conv_2d(
convnet, conv2_filter_count, filter_size, activation='relu')
convnet = max_pool_2d(convnet, pooling_kernel_size)
convnet = fully_connected(convnet, fc_units, activation='relu')
convnet = dropout(convnet, keep_probability)
convnet = fully_connected(
convnet, fully_connected_units, activation='softmax')
convnet = regression(
convnet,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='targets')
return convnet
def do_cnn_word2vec_2d(trainX, testX, trainY, testY):
global max_features
global max_document_length
print "CNN and word2vec2d"
y_test = testY
#trainX = pad_sequences(trainX, maxlen=max_features, value=0.)
#testX = pad_sequences(testX, maxlen=max_features, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY, nb_classes=2)
testY = to_categorical(testY, nb_classes=2)
# Building convolutional network
network = input_data(shape=[None,max_document_length,max_features,1], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 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, 2, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.01,
loss='categorical_crossentropy', name='target')
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit(trainX, trainY,
n_epoch=5, shuffle=True, validation_set=(testX, testY),
show_metric=True,run_id="sms")
y_predict_list = model.predict(testX)
print y_predict_list
y_predict = []
for i in y_predict_list:
print i[0]
if i[0] > 0.5:
y_predict.append(0)
else:
y_predict.append(1)
print(classification_report(y_test, y_predict))
print metrics.confusion_matrix(y_test, y_predict)
def vggnet():
X, Y = oxflower17.load_data(one_hot=True,resize_pics=(227, 227))
# Building 'VGG Network'
network = input_data(shape=[None, 227, 227, 3])
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, 17, activation='softmax')
network = regression(network, optimizer='rmsprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
# Training
model = tflearn.DNN(network, checkpoint_path='model_vgg',
max_checkpoints=1, tensorboard_verbose=0)
model.fit(X, Y, n_epoch=500, shuffle=True,
show_metric=True, batch_size=32, snapshot_step=500,
snapshot_epoch=False, run_id='vgg')
def build_model_2_conv(learning_rate, input_shape, nb_classes, base_path, drop):
network = input_data(shape=input_shape, name='input')
network = conv_2d(network, 64, [4, 16], activation='relu')
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, [4, 16], activation='relu')
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='relu')
network = dropout(network, drop)
network = fully_connected(network, 64, activation='relu')
network = dropout(network, drop)
network = fully_connected(network, nb_classes, activation='softmax')
network = regression(network, optimizer='sgd', learning_rate=learning_rate,
loss='categorical_crossentropy', name='target')
model = tflearn.DNN(network, tensorboard_verbose=3, tensorboard_dir=base_path + "/tflearn_logs/",
checkpoint_path=base_path + "/checkpoints/step")
return model
def create_model(learning_rate, input_shape, nb_classes, base_path, drop=1):
network = input_data(shape=input_shape, name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network, 128, activation='tanh')
network = dropout(network, drop)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, drop)
network = fully_connected(network, nb_classes, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=learning_rate,
loss='categorical_crossentropy', name='target')
model = tflearn.DNN(network, tensorboard_verbose=0, checkpoint_path=base_path + "/checkpoints/step")
return model
def main():
"""
Trains a CNN architecture and plots the results over a validation set.
Returns:
"""
# Load the SDR and hist data
data = load_data('reverb_pan_full_sdr.txt', 'pickle/')
# split data into train and test sets
test_percent = 0.15
train, test, validate = split_into_sets(len(data['sdr']), 1-test_percent,
test_percent, 0)
x_train = np.expand_dims([data['input'][i] for i in train], -1)
y_train = np.expand_dims([data['sdr'][i] for i in train], -1)
x_test = np.expand_dims([data['input'][i] for i in test], -1)
y_test = np.expand_dims([data['sdr'][i] for i in test], -1)
# construct the CNN.
inp = input_data(shape=[None, 50, 50, 1], name='input')
# two convolutional layers with max pooling
conv1 = conv_2d(inp, 32, [5, 5], activation='relu', regularizer="L2")
max_pool = max_pool_2d(conv1, 2)
conv2 = conv_2d(max_pool, 64, [5, 5], activation='relu', regularizer="L2")
max_pool2 = max_pool_2d(conv2, 2)
# two fully connected layers
full = fully_connected(max_pool2, 128, activation='tanh')
full = dropout(full, 0.8)
full2 = fully_connected(full, 256, activation='tanh')
full2 = dropout(full2, 0.8)
# output regression node
out = fully_connected(full2, 1, activation='linear')
network = regression(out, optimizer='sgd', learning_rate=0.01, name='target', loss='mean_square')
model = tflearn.DNN(network, tensorboard_verbose=1, checkpoint_path='checkpoint.p',
tensorboard_dir='tmp/tflearn_logs/')
model.fit({'input': x_train}, {'target': y_train}, n_epoch=1000, validation_set=(x_test, y_test),
snapshot_step=10000, run_id='convnet_duet_3x3')
predicted = np.array(model.predict(x_test))[:,0]
plot(y_test, predicted)
def train_neural_net(convolution_patch_size,
bands_to_use,
image_size,
train_images,
train_labels,
test_images,
test_labels,
number_of_batches,
batch_size):
on_band_count = 0
for b in bands_to_use:
if b == 1:
on_band_count += 1
train_images = train_images.astype(numpy.float32)
train_images = (train_images - 127.5) / 127.5
test_images = test_images.astype(numpy.float32)
test_images = (test_images - 127.5) / 127.5
# Convolutional network building
network = input_data(shape=[None, image_size, image_size, on_band_count])
network = conv_2d(network, 32, convolution_patch_size, activation='relu')
network = max_pool_2d(network, 2)
network = conv_2d(network, 64, convolution_patch_size, activation='relu')
network = conv_2d(network, 64, convolution_patch_size, 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)
# batch_size was originally 96
# n_epoch was originally 50
# each epoch is 170 steps I think
# Train using classifier
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit(train_images, train_labels, n_epoch=int(number_of_batches/100), shuffle=False, validation_set=(test_images, test_labels),
show_metric=True, batch_size=batch_size, run_id='cifar10_cnn')
return model.predict(test_images)
def cnn():
network = input_data(shape=[None, IMAGE_HEIGHT, IMAGE_WIDTH, 1], name='input')
network = conv_2d(network, 8, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = batch_normalization(network)
network = conv_2d(network, 16, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = batch_normalization(network)
network = conv_2d(network, 16, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = batch_normalization(network)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation='tanh')
network = dropout(network, 0.8)
network = fully_connected(network, CODE_LEN * MAX_CHAR, activation='softmax')
network = regression(network, optimizer='adam', learning_rate=0.001,
loss='categorical_crossentropy', name='target')
return network
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 create_cnn_layers():
shape = [None, IMAGE_STD_HEIGHT, IMAGE_STD_WIDTH, RGB_COLOR_COUNT]
# input_layer = Input(name='input', shape=shape)
input_layer = input_data(name='input', shape=shape)
# h = Convolution2D(22, 5, 5, activation='relu', dim_ordering=dim_ordering)(input_layer)
h = conv_2d_specialized(input_layer, 22, [5, 5])
POOL_SIZE = [2, 2]
# h = MaxPooling2D(pool_size=POOL_SIZE)(h)
h = max_pool_2d(h, POOL_SIZE, padding='valid')
h = local_response_normalization(h)
# h = Convolution2D(44, 3, 3, activation='relu', dim_ordering=dim_ordering)(h)
h = conv_2d_specialized(h, 44, [3, 3])
# h = MaxPooling2D(pool_size=POOL_SIZE)(h)
h = max_pool_2d(h, POOL_SIZE, padding='valid')
h = local_response_normalization(h)
# h = Dropout(0.25)(h)
h = dropout(h, 1-0.25)
# last_cnn_layer = Flatten()(h)
last_cnn_layer = flatten(h)
return input_layer, last_cnn_layer
def stop_dnn():
img_pre_processing = ImagePreprocessing()
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=10.)
network = input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_pre_processing,
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)
return network
def create_alexnet(num_classes, restore=False):
# Building 'AlexNet'
network = input_data(shape=[None, 224, 224, 3])
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 = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
return network
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')
h5f = h5py.File('dataset.h5', 'r')
X = h5f['X']
Y = h5f['Y']
#img_aug = tflearn.ImageAugmentation()
#img_aug.add_random_flip_leftright()
#img_aug.add_random_90degrees_rotation (rotations=[0, 2])
network = input_data(shape=[None, 300, 300, 3])
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,
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tflearn.datasets.mnist as mnist
if __name__ == '__main__':
x, y, test_x, test_y = mnist.load_data(one_hot=True)
x = x.reshape([-1, 28, 28, 1])
test_x = test_x.reshape([-1, 28, 28, 1])
input_data = input_data(shape=[None, 28, 28, 1], name='input')
# nb_filter表示输出通道数，filter_size表示卷积核大小5x5
conv1 = conv_2d(input_data, nb_filter=32, filter_size=5, activation='relu')
# kernel_size表示池化窗口大小2x2
pool1 = max_pool_2d(conv1, kernel_size=2)
conv2 = conv_2d(pool1, nb_filter=64, filter_size=5, activation='relu')
pool2 = max_pool_2d(conv2, kernel_size=2)
fc = fully_connected(pool2, n_units=1024, activation='relu')
fc = dropout(fc, 0.8)
output = fully_connected(fc, n_units=10, activation='softmax')
network = regression(output,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='targets')
X_train, y_train, X_test, y_test = mnist.load_data(
data_dir="/home/user/dataset/MNIST_data/", one_hot=True)
X_train = X_train.reshape([-1, 28, 28, 1])
X_test = X_test.reshape([-1, 28, 28, 1])
# define a placholder to recv data
net = input_data(shape=[None, 28, 28, 1], name="input")
# layer1
net = conv_2d(net,
nb_filter=32,
filter_size=[5, 5],
activation="relu",
padding='same')
net = max_pool_2d(
net, kernel_size=[2, 2]) # strides default to be the same as kernel_size
# layer2
net = conv_2d(net,
nb_filter=64,
filter_size=[5, 5],
activation="relu",
padding='same')
net = max_pool_2d(net, kernel_size=[2, 2])
####################################################################
# No need to reshape
####################################################################
# layer3
net = fully_connected(net, n_units=500, activation="relu")
params = {
'conv_filter': 5,
'pool_width': 3,
'pool_stride': 2,
'epoch': 50,
'id': 'cnn_try'
}
# Build CNN
input_data = input_data(shape=[None, 32, 32, 3], data_augmentation=img_aug)
conv1 = conv_2d(input_data,
64,
params['conv_filter'],
activation='relu',
regularizer='L2')
pool1 = max_pool_2d(conv1, params['pool_width'], params['pool_stride'])
lrn1 = local_response_normalization(pool1)
conv2 = conv_2d(lrn1,
64,
params['conv_filter'],
activation='relu',
regularizer='L2')
pool2 = max_pool_2d(conv2, params['pool_width'], params['pool_stride'])
lrn2 = local_response_normalization(pool2)
conv3 = conv_2d(lrn2,
128,
params['conv_filter'],
activation='relu',
regularizer='L2')
#conda install tflearn or pip install tflearn import tflearn from tflearn.layers.conv import conv_2d, max_pool_2d from tflearn.layers.core import input_data, fully_connected, dropout from tflearn.layers.estimator import regression # In[7]: model = input_data(shape=[None, 50, 50, 1], name='input') # In[8]: #first convolution Layer model = conv_2d(model, 46, 5, activation='relu') model = max_pool_2d(model, 5) #second Convolution Layer model = conv_2d(model, 42, 5, activation='relu') model = max_pool_2d(model, 5) #third Convolution Layer model = conv_2d(model, 38, 5, activation='relu') model = max_pool_2d(model, 5) #fully Connected Layer model = fully_connected(model, 1024, activation='relu') model = dropout(model, 0.7) model = fully_connected(model, 2, activation='softmax')
np.save('test_data.npy', testing_data)
return testing_data
train_data = create_train_data()
train_data = np.load('train_data.npy')
# Convolutional Neural Network
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
#saving our model after every session, and reloading it if we have a saved version
if os.path.exists('{}.meta'.format(MODEL_NAME)):
def create_googlenet(num_classes):
# Building 'GoogleNet'
network = input_data(shape=[None, 227, 227, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
conv1_7_7 = conv_2d(network, 64, 7, strides=2, activation='relu', name='conv1_7_7_s2')
pool1_3_3 = max_pool_2d(conv1_7_7, 3, strides=2)
pool1_3_3 = local_response_normalization(pool1_3_3)
conv2_3_3_reduce = conv_2d(pool1_3_3, 64, 1, activation='relu', name='conv2_3_3_reduce')
conv2_3_3 = conv_2d(conv2_3_3_reduce, 192, 3, activation='relu', name='conv2_3_3')
conv2_3_3 = local_response_normalization(conv2_3_3)
pool2_3_3 = max_pool_2d(conv2_3_3, kernel_size=3, strides=2, name='pool2_3_3_s2')
# 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, num_classes, activation='softmax')
network = regression(loss, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.01)
return network
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import pyautogui
cam = cv2.VideoCapture(0)
cam.set(3, 200)
cam.set(4, 200)
#cam.set(cv2.CAP_PROP_FPS, 3)
img_size = 224
boolean = 1
KEY = 0
convnet = input_data(shape=[None, img_size, img_size, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
MaxPool2D_1 = max_pool_2d(convnet, 5)
convnet = fully_connected(MaxPool2D_1, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
learning_rate=0.0001,
loss='categorical_crossentropy',
name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
(IMG_SIZE, IMG_SIZE)) # Resizing the image to 64*64
training_data.append([np.array(img), np.array(label)])
shuffle(training_data)
np.save('train_data.npy', training_data)
return training_data
#############################################################################
# Building the model
tf.reset_default_graph()
train_data = create_train_data()
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 3], name='input')
convnet = conv_2d(
convnet, 32, 5,
activation='relu') # Convolution Layer-1 with 5 Filters of size 32*32
convnet = max_pool_2d(convnet, 5) # Max Pooling with filter size of 5*5
convnet = conv_2d(
convnet, 64, 5,
activation='relu') # Convolution Layer-2 with 5 Filters of size 64*64
convnet = max_pool_2d(convnet, 5) # Max pooling with filter size of 5*5
convnet = conv_2d(
convnet, 32, 5,
activation='relu') # Convolution Layer-3 with 5 Filters of size 32*32
convnet = max_pool_2d(convnet, 5) # Max pooling with filter size of 5*5
convnet = fully_connected(
convnet, 1024,
activation='relu') # Fully Connected Layer-4 with 1024 neurons
convnet = dropout(convnet, 0.4) # Dropout rate set to 0.4
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
train_y.append(training[img][1])
for img in range(len(testing)):
test_x.append((testing[img][0]))
test_y.append(testing[img][1])
print(np.array(train_x).shape)
print(np.array(train_y).shape)
train_x = np.array(train_x).reshape(3686, 128, 128, 1)
train_y = np.array(train_y)
test_x = np.array(test_x).reshape(1579, 128, 128, 1)
test_y = np.array(test_y)
print(type(train_x))
convnet = input_data(shape=[None, 128, 128, 1], name='input')
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, kernel_size=2, strides=2)
convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, kernel_size=2, strides=2)
convnet = conv_2d(convnet, 128, 3, activation='relu')
convnet = max_pool_2d(convnet, kernel_size=2, strides=2)
convnet = conv_2d(convnet, 256, 3, activation='relu')
convnet = max_pool_2d(convnet, kernel_size=2, strides=2)
convnet = fully_connected(convnet, 4096, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2048, activation='relu')
convnet = dropout(convnet, 0.8)
def analysis(filepath):
verify_data = process_verify_data(filepath)
str_label = "Cannot make a prediction."
status = "Error"
tf.reset_default_graph()
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 3], name='input')
'''
# relu:
Relu is used in the middle / hidden layers of the network to regularize the activation.
It is essentialy the function: max(0, x)
Activation should not be in negative, either it should be zero or more than that.
# softmax:
Softmax is used for the output layer in multi class classification problems.
It is essentialy the function: log(1 + e^x)
It outputs a vector of probabilities of each class.
'''
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 128, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 4, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print ('Model loaded successfully.')
else:
print ('Error: Create a model using neural_network.py first.')
img_data, img_name = verify_data[0], verify_data[1]
orig = img_data
data = img_data.reshape(IMG_SIZE, IMG_SIZE, 3)
model_out = model.predict([data])[0]
if np.argmax(model_out) == 0: str_label = 'Healthy'
elif np.argmax(model_out) == 1: str_label = 'Bacterial'
elif np.argmax(model_out) == 2: str_label = 'Viral'
elif np.argmax(model_out) == 3: str_label = 'Lateblight'
if str_label =='Healthy': status = 'Healthy'
else: status = 'Unhealthy'
result = 'Status: ' + status + '.'
if (str_label != 'Healthy'): result += '\nDisease: ' + str_label + '.'
return result
testy = pd.read_csv("data/csvTestLabel 10k x 1.csv", header=None)
#Process data
trainx = trainx.values.astype('float32').reshape([-1, 28, 28, 1])
testx = testx.values.astype('float32').reshape([-1, 28, 28, 1])
trainy = trainy.values.astype('int32')
trainy = to_categorical(trainy, 10)
testy = testy.values.astype('int32')
testy = to_categorical(testy, 10)
# Building convolutional network
network = input_data(shape=[None, 28, 28, 1], name='input')
network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
network = max_pool_2d(network, 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, 10, activation='softmax')
network = regression(network,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='target')
# Modified by: Ajinkya Malhotra
#
# Model that defines all the architecture used for the neural network
import tflearn
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.metrics import Accuracy
acc = Accuracy()
network = input_data(shape=[None, 100, 100, 1])
# Conv layers ------------------------------------
network = conv_2d(network, 64, 3, strides=1, activation='tanh')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 64, 3, strides=1, activation='tanh')
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 64, 3, strides=1, activation='tanh')
network = conv_2d(network, 64, 3, strides=1, activation='relu')
network = conv_2d(network, 64, 3, strides=1, activation='relu')
network = max_pool_2d(network, 2, strides=2)
# Fully Connected Layers -------------------------
network = fully_connected(network, 1024, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 1024, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 7, activation='softmax')
network = regression(network,
optimizer='momentum',
def construct_inceptionv1onfire(x, y):
# from Dunnings/Breckon research paper 2018
network = input_data(shape=[None, y, x, 3])
conv1_7_7 = conv_2d(network,
64,
5,
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,
128,
3,
activation='relu',
name='conv2_3_3')
conv2_3_3 = local_response_normalization(conv2_3_3)
pool2_3_3 = max_pool_2d(conv2_3_3,
kernel_size=3,
strides=2,
name='pool2_3_3_s2')
inception_3a_1_1 = conv_2d(pool2_3_3,
64,
1,
activation='relu',
name='inception_3a_1_1')
inception_3a_3_3_reduce = conv_2d(pool2_3_3,
96,
1,
activation='relu',
name='inception_3a_3_3_reduce')
inception_3a_3_3 = conv_2d(inception_3a_3_3_reduce,
128,
filter_size=3,
activation='relu',
name='inception_3a_3_3')
inception_3a_5_5_reduce = conv_2d(pool2_3_3,
16,
filter_size=1,
activation='relu',
name='inception_3a_5_5_reduce')
inception_3a_5_5 = conv_2d(inception_3a_5_5_reduce,
32,
filter_size=5,
activation='relu',
name='inception_3a_5_5')
inception_3a_pool = max_pool_2d(
pool2_3_3,
kernel_size=3,
strides=1,
)
inception_3a_pool_1_1 = conv_2d(inception_3a_pool,
32,
filter_size=1,
activation='relu',
name='inception_3a_pool_1_1')
# merge the inception_3a__
inception_3a_output = merge([
inception_3a_1_1, inception_3a_3_3, inception_3a_5_5,
inception_3a_pool_1_1
],
mode='concat',
axis=3)
inception_3b_1_1 = conv_2d(inception_3a_output,
128,
filter_size=1,
activation='relu',
name='inception_3b_1_1')
inception_3b_3_3_reduce = conv_2d(inception_3a_output,
128,
filter_size=1,
activation='relu',
name='inception_3b_3_3_reduce')
inception_3b_3_3 = conv_2d(inception_3b_3_3_reduce,
192,
filter_size=3,
activation='relu',
name='inception_3b_3_3')
inception_3b_5_5_reduce = conv_2d(inception_3a_output,
32,
filter_size=1,
activation='relu',
name='inception_3b_5_5_reduce')
inception_3b_5_5 = conv_2d(inception_3b_5_5_reduce,
96,
filter_size=5,
name='inception_3b_5_5')
inception_3b_pool = max_pool_2d(inception_3a_output,
kernel_size=3,
strides=1,
name='inception_3b_pool')
inception_3b_pool_1_1 = conv_2d(inception_3b_pool,
64,
filter_size=1,
activation='relu',
name='inception_3b_pool_1_1')
#merge the inception_3b_*
inception_3b_output = merge([
inception_3b_1_1, inception_3b_3_3, inception_3b_5_5,
inception_3b_pool_1_1
],
mode='concat',
axis=3,
name='inception_3b_output')
pool3_3_3 = max_pool_2d(inception_3b_output,
kernel_size=3,
strides=2,
name='pool3_3_3')
inception_4a_1_1 = conv_2d(pool3_3_3,
192,
filter_size=1,
activation='relu',
name='inception_4a_1_1')
inception_4a_3_3_reduce = conv_2d(pool3_3_3,
96,
filter_size=1,
activation='relu',
name='inception_4a_3_3_reduce')
inception_4a_3_3 = conv_2d(inception_4a_3_3_reduce,
208,
filter_size=3,
activation='relu',
name='inception_4a_3_3')
inception_4a_5_5_reduce = conv_2d(pool3_3_3,
16,
filter_size=1,
activation='relu',
name='inception_4a_5_5_reduce')
inception_4a_5_5 = conv_2d(inception_4a_5_5_reduce,
48,
filter_size=5,
activation='relu',
name='inception_4a_5_5')
inception_4a_pool = max_pool_2d(pool3_3_3,
kernel_size=3,
strides=1,
name='inception_4a_pool')
inception_4a_pool_1_1 = conv_2d(inception_4a_pool,
64,
filter_size=1,
activation='relu',
name='inception_4a_pool_1_1')
inception_4a_output = merge([
inception_4a_1_1, inception_4a_3_3, inception_4a_5_5,
inception_4a_pool_1_1
],
mode='concat',
axis=3,
name='inception_4a_output')
pool5_7_7 = avg_pool_2d(inception_4a_output, kernel_size=5, strides=1)
pool5_7_7 = dropout(pool5_7_7, 0.4)
loss = fully_connected(pool5_7_7, 2, activation='softmax')
network = regression(loss,
optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.001)
model = tflearn.DNN(network,
checkpoint_path='sp-inceptiononv1onfire',
max_checkpoints=1,
tensorboard_verbose=2)
return model
normalize=True)
X_test = np.reshape(X_test, (-1, 128, 128, 3))
X_test = cv2.imread('1.bmp')
x = io.imread(X_test).reshape((128, 128, 3)).astype(np.float) / 255
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center()
img_prep.add_featurewise_stdnorm()
convnet = input_data(shape=[None, 128, 128, 3],
data_preprocessing=img_prep,
name='input')
convnet = conv_2d(convnet, 32, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = conv_2d(convnet, 64, 2, activation='relu')
convnet = max_pool_2d(convnet, 2)
convnet = fully_connected(convnet, 512, activation='relu')
convnet = dropout(convnet, 0.6)
convnet = fully_connected(convnet, 4, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='targets')
model = tflearn.DNN(convnet)
def inceptionv3(width, height, frame_count, lr, output=9, model_name = 'inceptionv3.model'):
network = input_data(shape=[None, width, height,3], name='input')
conv1_7_7 = conv_2d(network, 64, 28, strides=4, activation='relu', name = 'conv1_7_7_s2')
pool1_3_3 = max_pool_2d(conv1_7_7, 9,strides=4)
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, 192,12, 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=12, strides=2, name='pool2_3_3_s2')
inception_3a_1_1 = conv_2d(pool2_3_3, 64, 1, activation='relu', name='inception_3a_1_1')
inception_3a_3_3_reduce = conv_2d(pool2_3_3, 96,1, activation='relu', name='inception_3a_3_3_reduce')
inception_3a_3_3 = conv_2d(inception_3a_3_3_reduce, 128,filter_size=12, 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=15, activation='relu', name= 'inception_3a_5_5')
inception_3a_pool = max_pool_2d(pool2_3_3, kernel_size=12, strides=1, )
inception_3a_pool_1_1 = conv_2d(inception_3a_pool, 32, filter_size=1, activation='relu', name='inception_3a_pool_1_1')
# merge the inception_3a__
inception_3a_output = merge([inception_3a_1_1, inception_3a_3_3, inception_3a_5_5, inception_3a_pool_1_1], mode='concat', axis=3)
inception_3b_1_1 = conv_2d(inception_3a_output, 128,filter_size=1,activation='relu', name= 'inception_3b_1_1' )
inception_3b_3_3_reduce = conv_2d(inception_3a_output, 128, filter_size=1, activation='relu', name='inception_3b_3_3_reduce')
inception_3b_3_3 = conv_2d(inception_3b_3_3_reduce, 192, filter_size=9, 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=15, name = 'inception_3b_5_5')
inception_3b_pool = max_pool_2d(inception_3a_output, kernel_size=12, strides=1, name='inception_3b_pool')
inception_3b_pool_1_1 = conv_2d(inception_3b_pool, 64, filter_size=1,activation='relu', name='inception_3b_pool_1_1')
#merge the inception_3b_*
inception_3b_output = merge([inception_3b_1_1, inception_3b_3_3, inception_3b_5_5, inception_3b_pool_1_1], mode='concat',axis=3,name='inception_3b_output')
pool3_3_3 = max_pool_2d(inception_3b_output, kernel_size=3, strides=2, name='pool3_3_3')
inception_4a_1_1 = conv_2d(pool3_3_3, 192, filter_size=1, activation='relu', name='inception_4a_1_1')
inception_4a_3_3_reduce = conv_2d(pool3_3_3, 96, filter_size=1, activation='relu', name='inception_4a_3_3_reduce')
inception_4a_3_3 = conv_2d(inception_4a_3_3_reduce, 208, filter_size=3, activation='relu', name='inception_4a_3_3')
inception_4a_5_5_reduce = conv_2d(pool3_3_3, 16, filter_size=1, activation='relu', name='inception_4a_5_5_reduce')
inception_4a_5_5 = conv_2d(inception_4a_5_5_reduce, 48, filter_size=5, activation='relu', name='inception_4a_5_5')
inception_4a_pool = max_pool_2d(pool3_3_3, kernel_size=3, strides=1, name='inception_4a_pool')
inception_4a_pool_1_1 = conv_2d(inception_4a_pool, 64, filter_size=1, activation='relu', name='inception_4a_pool_1_1')
inception_4a_output = merge([inception_4a_1_1, inception_4a_3_3, inception_4a_5_5, inception_4a_pool_1_1], mode='concat', axis=3, name='inception_4a_output')
inception_4b_1_1 = conv_2d(inception_4a_output, 160, filter_size=1, activation='relu', name='inception_4a_1_1')
inception_4b_3_3_reduce = conv_2d(inception_4a_output, 112, filter_size=1, activation='relu', name='inception_4b_3_3_reduce')
inception_4b_3_3 = conv_2d(inception_4b_3_3_reduce, 224, filter_size=3, activation='relu', name='inception_4b_3_3')
inception_4b_5_5_reduce = conv_2d(inception_4a_output, 24, filter_size=1, activation='relu', name='inception_4b_5_5_reduce')
inception_4b_5_5 = conv_2d(inception_4b_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4b_5_5')
inception_4b_pool = max_pool_2d(inception_4a_output, kernel_size=3, strides=1, name='inception_4b_pool')
inception_4b_pool_1_1 = conv_2d(inception_4b_pool, 64, filter_size=1, activation='relu', name='inception_4b_pool_1_1')
inception_4b_output = merge([inception_4b_1_1, inception_4b_3_3, inception_4b_5_5, inception_4b_pool_1_1], mode='concat', axis=3, name='inception_4b_output')
inception_4c_1_1 = conv_2d(inception_4b_output, 128, filter_size=1, activation='relu',name='inception_4c_1_1')
inception_4c_3_3_reduce = conv_2d(inception_4b_output, 128, filter_size=1, activation='relu', name='inception_4c_3_3_reduce')
inception_4c_3_3 = conv_2d(inception_4c_3_3_reduce, 256, filter_size=3, activation='relu', name='inception_4c_3_3')
inception_4c_5_5_reduce = conv_2d(inception_4b_output, 24, filter_size=1, activation='relu', name='inception_4c_5_5_reduce')
inception_4c_5_5 = conv_2d(inception_4c_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4c_5_5')
inception_4c_pool = max_pool_2d(inception_4b_output, kernel_size=3, strides=1)
inception_4c_pool_1_1 = conv_2d(inception_4c_pool, 64, filter_size=1, activation='relu', name='inception_4c_pool_1_1')
inception_4c_output = merge([inception_4c_1_1, inception_4c_3_3, inception_4c_5_5, inception_4c_pool_1_1], mode='concat', axis=3,name='inception_4c_output')
inception_4d_1_1 = conv_2d(inception_4c_output, 112, filter_size=1, activation='relu', name='inception_4d_1_1')
inception_4d_3_3_reduce = conv_2d(inception_4c_output, 144, filter_size=1, activation='relu', name='inception_4d_3_3_reduce')
inception_4d_3_3 = conv_2d(inception_4d_3_3_reduce, 288, filter_size=3, activation='relu', name='inception_4d_3_3')
inception_4d_5_5_reduce = conv_2d(inception_4c_output, 32, filter_size=1, activation='relu', name='inception_4d_5_5_reduce')
inception_4d_5_5 = conv_2d(inception_4d_5_5_reduce, 64, filter_size=5, activation='relu', name='inception_4d_5_5')
inception_4d_pool = max_pool_2d(inception_4c_output, kernel_size=3, strides=1, name='inception_4d_pool')
inception_4d_pool_1_1 = conv_2d(inception_4d_pool, 64, filter_size=1, activation='relu', name='inception_4d_pool_1_1')
inception_4d_output = merge([inception_4d_1_1, inception_4d_3_3, inception_4d_5_5, inception_4d_pool_1_1], mode='concat', axis=3, name='inception_4d_output')
inception_4e_1_1 = conv_2d(inception_4d_output, 256, filter_size=1, activation='relu', name='inception_4e_1_1')
inception_4e_3_3_reduce = conv_2d(inception_4d_output, 160, filter_size=1, activation='relu', name='inception_4e_3_3_reduce')
inception_4e_3_3 = conv_2d(inception_4e_3_3_reduce, 320, filter_size=3, activation='relu', name='inception_4e_3_3')
inception_4e_5_5_reduce = conv_2d(inception_4d_output, 32, filter_size=1, activation='relu', name='inception_4e_5_5_reduce')
inception_4e_5_5 = conv_2d(inception_4e_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_4e_5_5')
inception_4e_pool = max_pool_2d(inception_4d_output, kernel_size=3, strides=1, name='inception_4e_pool')
inception_4e_pool_1_1 = conv_2d(inception_4e_pool, 128, filter_size=1, activation='relu', name='inception_4e_pool_1_1')
inception_4e_output = merge([inception_4e_1_1, inception_4e_3_3, inception_4e_5_5,inception_4e_pool_1_1],axis=3, mode='concat')
pool4_3_3 = max_pool_2d(inception_4e_output, kernel_size=3, strides=2, name='pool_3_3')
inception_5a_1_1 = conv_2d(pool4_3_3, 256, filter_size=1, activation='relu', name='inception_5a_1_1')
inception_5a_3_3_reduce = conv_2d(pool4_3_3, 160, filter_size=1, activation='relu', name='inception_5a_3_3_reduce')
inception_5a_3_3 = conv_2d(inception_5a_3_3_reduce, 320, filter_size=3, activation='relu', name='inception_5a_3_3')
inception_5a_5_5_reduce = conv_2d(pool4_3_3, 32, filter_size=1, activation='relu', name='inception_5a_5_5_reduce')
inception_5a_5_5 = conv_2d(inception_5a_5_5_reduce, 128, filter_size=5, activation='relu', name='inception_5a_5_5')
inception_5a_pool = max_pool_2d(pool4_3_3, kernel_size=3, strides=1, name='inception_5a_pool')
inception_5a_pool_1_1 = conv_2d(inception_5a_pool, 128, filter_size=1,activation='relu', name='inception_5a_pool_1_1')
inception_5a_output = merge([inception_5a_1_1, inception_5a_3_3, inception_5a_5_5, inception_5a_pool_1_1], axis=3,mode='concat')
inception_5b_1_1 = conv_2d(inception_5a_output, 384, filter_size=1,activation='relu', name='inception_5b_1_1')
inception_5b_3_3_reduce = conv_2d(inception_5a_output, 192, filter_size=1, activation='relu', name='inception_5b_3_3_reduce')
inception_5b_3_3 = conv_2d(inception_5b_3_3_reduce, 384, filter_size=3,activation='relu', name='inception_5b_3_3')
inception_5b_5_5_reduce = conv_2d(inception_5a_output, 48, filter_size=1, activation='relu', name='inception_5b_5_5_reduce')
inception_5b_5_5 = conv_2d(inception_5b_5_5_reduce,128, filter_size=5, activation='relu', name='inception_5b_5_5' )
inception_5b_pool = max_pool_2d(inception_5a_output, kernel_size=3, strides=1, name='inception_5b_pool')
inception_5b_pool_1_1 = conv_2d(inception_5b_pool, 128, filter_size=1, activation='relu', name='inception_5b_pool_1_1')
inception_5b_output = merge([inception_5b_1_1, inception_5b_3_3, inception_5b_5_5, inception_5b_pool_1_1], axis=3, mode='concat')
pool5_7_7 = avg_pool_2d(inception_5b_output, kernel_size=7, strides=1)
pool5_7_7 = dropout(pool5_7_7, 0.45)
loss = fully_connected(pool5_7_7, output,activation='softmax')
network = regression(loss, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=lr, name='targets')
model = tflearn.DNN(network,
max_checkpoints=0, tensorboard_verbose=0,tensorboard_dir='log')
return model
def analysis():
import cv2
import numpy as np
import os
from random import shuffle
from tqdm import \
tqdm
verify_dir = 'testpicture'
IMG_SIZE = 50
LR = 1e-3
MODEL_NAME = 'healthyvsunhealthy-{}-{}.model'.format(LR, '2conv-basic')
def process_verify_data():
verifying_data = []
for img in tqdm(os.listdir(verify_dir)):
path = os.path.join(verify_dir, img)
img_num = img.split('.')[0]
img = cv2.imread(path, cv2.IMREAD_COLOR)
img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))
verifying_data.append([np.array(img), img_num])
np.save('verify_data.npy', verifying_data)
return verifying_data
verify_data = process_verify_data()
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tensorflow as tf
tf.reset_default_graph()
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 3], name='input')
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 128, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 4, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
learning_rate=LR,
loss='categorical_crossentropy',
name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('model loaded!')
import matplotlib.pyplot as plt
fig = plt.figure()
for num, data in enumerate(verify_data):
img_num = data[1]
img_data = data[0]
y = fig.add_subplot(3, 4, num + 1)
orig = img_data
data = img_data.reshape(IMG_SIZE, IMG_SIZE, 3)
# model_out = model.predict([data])[0]
model_out = model.predict([data])[0]
if np.argmax(model_out) == 0:
str_label = 'healthy'
elif np.argmax(model_out) == 1:
str_label = 'bacterial'
elif np.argmax(model_out) == 2:
str_label = 'viral'
elif np.argmax(model_out) == 3:
str_label = 'lateblight'
if str_label == 'healthy':
status = "HEALTHY"
else:
status = "UNHEALTHY"
message = tk.Label(text='Status: ' + status,
background="lightgreen",
fg="Brown",
font=("", 15))
message.grid(column=0, row=3, padx=10, pady=10)
if str_label == 'bacterial':
diseasename = "Bacterial Spot "
disease = tk.Label(text='Disease Name: ' + diseasename,
background="lightgreen",
fg="Black",
font=("", 15))
disease.grid(column=0, row=4, padx=10, pady=10)
r = tk.Label(text='Click below for remedies...',
background="lightgreen",
fg="Brown",
font=("", 15))
r.grid(column=0, row=5, padx=10, pady=10)
button3 = tk.Button(text="Remedies", command=bact)
button3.grid(column=0, row=6, padx=10, pady=10)
elif str_label == 'viral':
diseasename = "Yellow leaf curl virus "
disease = tk.Label(text='Disease Name: ' + diseasename,
background="lightgreen",
fg="Black",
font=("", 15))
disease.grid(column=0, row=4, padx=10, pady=10)
r = tk.Label(text='Click below for remedies...',
background="lightgreen",
fg="Brown",
font=("", 15))
r.grid(column=0, row=5, padx=10, pady=10)
button3 = tk.Button(text="Remedies", command=vir)
button3.grid(column=0, row=6, padx=10, pady=10)
elif str_label == 'lateblight':
diseasename = "Late Blight "
disease = tk.Label(text='Disease Name: ' + diseasename,
background="lightgreen",
fg="Black",
font=("", 15))
disease.grid(column=0, row=4, padx=10, pady=10)
r = tk.Label(text='Click below for remedies...',
background="lightgreen",
fg="Brown",
font=("", 15))
r.grid(column=0, row=5, padx=10, pady=10)
button3 = tk.Button(text="Remedies", command=latebl)
button3.grid(column=0, row=6, padx=10, pady=10)
else:
r = tk.Label(text='Plant is healthy',
background="lightgreen",
fg="Black",
font=("", 15))
r.grid(column=0, row=4, padx=10, pady=10)
button = tk.Button(text="Exit", command=exit)
button.grid(column=0, row=9, padx=20, pady=20)
def define_network(self):
"""
Defines CNN architecture
:return: CNN model
"""
# My CNN 1 (type1)
# # For data normalization
# img_prep = ImagePreprocessing()
# img_prep.add_featurewise_zero_center()
# img_prep.add_featurewise_stdnorm()
#
# # For creating extra data(increase dataset). Flipped, Rotated, Blurred and etc. images
# img_aug = ImageAugmentation()
# img_aug.add_random_flip_leftright()
# img_aug.add_random_rotation(max_angle=25.0)
# img_aug.add_random_blur(sigma_max=3.0)
#
# self.network = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1],
# data_augmentation=img_aug,
# data_preprocessing=img_prep)
# self.network = conv_2d(self.network, 64, 5, activation='relu')
# self.network = max_pool_2d(self.network, 3, strides=2)
# self.network = conv_2d(self.network, 64, 5, activation='relu')
# self.network = max_pool_2d(self.network, 3, strides=2)
# self.network = conv_2d(self.network, 128, 4, activation='relu')
# self.network = dropout(self.network, 0.3)
# self.network = fully_connected(self.network, 3072, activation='relu')
# self.network = fully_connected(self.network, len(EMOTIONS), activation='softmax')
# self.network = regression(self.network, optimizer='adam', loss='categorical_crossentropy')
# self.model = tflearn.DNN(self.network, checkpoint_path=os.path.join(CHECKPOINTS_PATH + '/emotion_recognition'),
# max_checkpoints=1, tensorboard_verbose=0)
# My CNN 2 (type2)
# For creating extra data(increase dataset). Flipped, Rotated, Blurred and etc. images
img_aug = ImageAugmentation()
img_aug.add_random_flip_leftright()
img_aug.add_random_rotation(max_angle=25.0)
img_aug.add_random_blur(sigma_max=3.0)
self.network = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1],
data_augmentation=img_aug)
self.network = conv_2d(self.network, 64, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 64, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = conv_2d(self.network, 128, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 128, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = dropout(self.network, 0.2)
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 256, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = dropout(self.network, 0.25)
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = conv_2d(self.network, 512, 3, activation='relu')
self.network = batch_normalization(self.network)
self.network = max_pool_2d(self.network, 2, strides=2)
self.network = dropout(self.network, 0.25)
self.network = fully_connected(self.network, 1024, activation='relu')
self.network = batch_normalization(self.network)
self.network = dropout(self.network, 0.45)
self.network = fully_connected(self.network, 1024, activation='relu')
self.network = batch_normalization(self.network)
self.network = dropout(self.network, 0.45)
self.network = fully_connected(self.network,
len(EMOTIONS),
activation='softmax')
self.network = regression(self.network,
optimizer='adam',
loss='categorical_crossentropy')
self.model = tflearn.DNN(
self.network,
checkpoint_path=os.path.join(CHECKPOINTS_PATH +
'/emotion_recognition'),
max_checkpoints=1,
tensorboard_verbose=0)
return self.model
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.normalization import local_response_normalization
from tflearn.layers.estimator import regression
# Data loading and basic transformations
import tflearn.datasets.mnist as mnist
data_dir = "datasets/MNIST"
X, Y, X_test, Y_test = mnist.load_data(data_dir=data_dir, one_hot=True)
X = X.reshape([-1, 28, 28, 1])
X_test = X_test.reshape([-1, 28, 28, 1])
# Building the network
CNN = input_data(shape=[None, 28, 28, 1], name='input')
CNN = conv_2d(CNN, 32, 5, activation='relu', regularizer='L2')
CNN = max_pool_2d(CNN, 2)
CNN = local_response_normalization(CNN)
CNN = conv_2d(CNN, 64, 5, activation='relu', regularizer='L2')
CNN = max_pool_2d(CNN, 2)
CNN = local_response_normalization(CNN)
CNN = fully_connected(CNN, 1024, activation=None)
CNN = dropout(CNN, 0.5)
CNN = fully_connected(CNN, 10, activation='softmax')
CNN = regression(CNN, optimizer='adam', learning_rate=0.0001,
loss='categorical_crossentropy', name='target')
# Training the network
def foo(img_fn, model_fn='../data/model/model_weights'):
img = cv2.imread(img_fn, cv2.IMREAD_GRAYSCALE)
haar_fn = '../data/haarcascade_russian_plate_number.xml'
haar = cv2.CascadeClassifier(haar_fn)
detected = haar.detectMultiScale(img)
plates = []
for x, y, w, h in detected:
obj = img[y:y + h, x:x + w]
plates.append(obj)
chars = plates[0] < filters.threshold_minimum(plates[0])
labeled_chars, a = ndi.label(chars)
labeled_chars = (labeled_chars > 1).astype(np.int8)
c = measure.find_contours(labeled_chars, .1)
letters = []
for i, v in enumerate(c):
xs, ys = zip(*[i for i in v])
x = int(min(xs))
y = int(min(ys))
w = int(max(xs) - x + 2)
h = int(max(ys) - y + 2)
if w < 15:
continue
letters.append((y, x, h, w))
letters = sorted(letters)
letters_img = [plates[0][x:x + w, y:y + h] for y, x, h, w in letters]
letters_img = [i for i in letters_img if i[0, 0] > 127]
sizes = [image.size for image in letters_img]
median = np.median(sizes)
allowed_size = median + median / 4
letters_img = [image for image in letters_img if image.size < allowed_size]
size = 64
normalized_img = []
for i in letters_img:
ratio = i.shape[0] / i.shape[1]
img1 = transform.resize(i, [size, int(size / ratio)], mode='constant')
width = img1.shape[1]
missing = (size - width) // 2
ones = np.ones([size, missing])
img2 = np.append(ones, img1, 1)
img3 = np.append(img2, ones, 1)
if 2 * missing + width != size:
one = np.ones([size, 1])
img4 = np.append(img3, one, 1)
else:
img4 = img3
normalized_img.append(img4 * 255)
net_input = input_data(shape=[None, 64, 64, 1])
conv1 = conv_2d(net_input,
nb_filter=4,
filter_size=5,
strides=[1, 1, 1, 1],
activation='relu')
max_pool1 = max_pool_2d(conv1, kernel_size=2)
conv2 = conv_2d(max_pool1,
nb_filter=8,
filter_size=5,
strides=[1, 2, 2, 1],
activation='relu')
max_pool2 = max_pool_2d(conv2, kernel_size=2)
conv3 = conv_2d(max_pool2,
nb_filter=12,
filter_size=4,
strides=[1, 1, 1, 1],
activation='relu')
max_pool3 = max_pool_2d(conv3, kernel_size=2)
fc1 = fully_connected(max_pool3, n_units=200, activation='relu')
drop1 = dropout(fc1, keep_prob=.5)
fc2 = fully_connected(drop1, n_units=36, activation='softmax')
net = regression(fc2)
model = DNN(network=net)
model.load(model_file=model_fn)
labels = list('ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789')
predicted = []
for i in normalized_img:
y = model.predict(i.reshape([1, 64, 64, 1]))
y_pred = np.argmax(y[0])
predicted.append(labels[y_pred])
return ''.join(predicted)
