def get_image_data(data_path, read_mode=None, training_ratio=0.8):
training_path = "/proc_training_set"
testing_path = "/proc_testing_set"
read_type = set_distinguisher(data_path, read_mode)['read_mode']
process_info = setwise_preprocessing(data_path, True)
input_shape = (process_info["height"], process_info["width"], 3)
input_single = (process_info["height"], process_info["width"])
num_classes = process_info["num_categories"]
loss_func = ""
if num_classes > 2:
loss_func = "categorical_crossentropy"
elif num_classes == 2:
loss_func = "binary_crossentropy"
train_data = ImageDataGenerator(rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_data = ImageDataGenerator(rescale=1. / 255)
X_train = train_data.flow_from_directory(
data_path + training_path,
target_size=input_single,
color_mode='rgb',
batch_size=(32 if process_info["train_size"] >= 32 else 1),
class_mode=loss_func[:loss_func.find("_")])
X_test = test_data.flow_from_directory(
data_path + testing_path,
target_size=input_single,
color_mode='rgb',
batch_size=(32 if process_info["test_size"] >= 32 else 1),
class_mode=loss_func[:loss_func.find("_")])
return X_train, X_test, process_info['height'], process_info[
'width'], num_classes
def convolutional(instruction=None,
read_mode=None,
preprocess=True,
verbose=0,
data_path=os.getcwd(),
new_folders=True,
image_column=None,
training_ratio=0.8,
augmentation=True,
epochs=10,
height=None,
width=None):
'''
Body of the convolutional function used that is called in the neural network query
if the data is presented in images.
:param many parameters: used to preprocess, tune, plot generation, and parameterizing the convolutional neural network trained.
:return dictionary that holds all the information for the finished model.
'''
logger("Generating datasets for classes")
if preprocess:
read_mode_info = set_distinguisher(data_path, read_mode)
read_mode = read_mode_info["read_mode"]
training_path = "/proc_training_set"
testing_path = "/proc_testing_set"
if read_mode == "setwise":
processInfo = setwise_preprocessing(data_path, new_folders, height,
width)
if not new_folders:
training_path = "/training_set"
testing_path = "/testing_set"
# if image dataset in form of csv
elif read_mode == "csvwise":
if training_ratio <= 0 or training_ratio >= 1:
raise BaseException(f"Test ratio must be between 0 and 1.")
processInfo = csv_preprocessing(read_mode_info["csv_path"],
data_path, instruction,
image_column, training_ratio,
height, width)
# if image dataset in form of one folder containing class folders
elif read_mode == "classwise":
if training_ratio <= 0 or training_ratio >= 1:
raise BaseException(f"Test ratio must be between 0 and 1.")
processInfo = classwise_preprocessing(data_path, training_ratio,
height, width)
else:
training_path = "/training_set"
testing_path = "/testing_set"
processInfo = already_processed(data_path)
num_channels = 3
color_mode = 'rgb'
if processInfo["gray_scale"]:
num_channels = 1
color_mode = 'grayscale'
input_shape = (processInfo["height"], processInfo["width"], num_channels)
input_single = (processInfo["height"], processInfo["width"])
num_classes = processInfo["num_categories"]
loss_func = ""
if num_classes > 2:
loss_func = "categorical_crossentropy"
elif num_classes == 2:
loss_func = "binary_crossentropy"
logger("Creating convolutional neural network dynamically")
# Convolutional Neural Network
model = Sequential()
# model.add(
# Conv2D(
# 64,
# kernel_size=3,
# activation="relu",
# input_shape=input_shape))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Conv2D(64, kernel_size=3, activation="relu"))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Flatten())
# model.add(Dense(num_classes, activation="softmax"))
# model.compile(
# optimizer="adam",
# loss=loss_func,
# metrics=['accuracy'])
model.add(
Conv2D(filters=64,
kernel_size=5,
activation="relu",
input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(filters=64, kernel_size=3, activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(filters=64, kernel_size=3, activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(units=256, activation="relu"))
model.add(Dropout(0.25))
model.add(Dense(units=num_classes, activation="softmax"))
model.compile(optimizer="adam", loss=loss_func, metrics=['accuracy'])
logger("Located image data")
if augmentation:
train_data = ImageDataGenerator(rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_data = ImageDataGenerator(rescale=1. / 255)
logger('Dataset augmented through zoom, shear, flip, and rescale')
else:
train_data = ImageDataGenerator()
test_data = ImageDataGenerator()
logger("->", "Optimal image size identified: {}".format(input_shape))
X_train = train_data.flow_from_directory(
data_path + training_path,
target_size=input_single,
color_mode=color_mode,
batch_size=(32 if processInfo["train_size"] >= 32 else 1),
class_mode=loss_func[:loss_func.find("_")])
X_test = test_data.flow_from_directory(
data_path + testing_path,
target_size=input_single,
color_mode=color_mode,
batch_size=(32 if processInfo["test_size"] >= 32 else 1),
class_mode=loss_func[:loss_func.find("_")])
if epochs < 0:
raise BaseException("Number of epochs has to be greater than 0.")
logger('Training image model')
history = model.fit_generator(
X_train,
steps_per_epoch=X_train.n // X_train.batch_size,
validation_data=X_test,
validation_steps=X_test.n // X_test.batch_size,
epochs=epochs,
verbose=verbose)
logger(
'->', 'Final training accuracy: {}'.format(
history.history['accuracy'][len(history.history['accuracy']) - 1]))
logger(
'->',
'Final validation accuracy: {}'.format(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1]))
# storing values the model dictionary
logger("Stored model under 'convolutional_NN' key")
clearLog()
return {
'id': generate_id(),
'data_type': read_mode,
'data_path': data_path,
'data': {
'train': X_train,
'test': X_test
},
'shape': input_shape,
"model": model,
'losses': {
'training_loss': history.history['loss'],
'val_loss': history.history['val_loss']
},
'accuracy': {
'training_accuracy': history.history['accuracy'],
'validation_accuracy': history.history['val_accuracy']
},
'num_classes': (2 if num_classes == 1 else num_classes),
'data_sizes': {
'train_size': processInfo['train_size'],
'test_size': processInfo['test_size']
}
}
def convolutional(instruction=None,
read_mode=None,
preprocess=True,
data_path=None,
verbose=0,
new_folders=True,
image_column=None,
training_ratio=0.8,
augmentation=True,
custom_arch=None,
pretrained=None,
epochs=10,
height=None,
width=None):
'''
Body of the convolutional function used that is called in the neural network query
if the data is presented in images.
:param many parameters: used to preprocess, tune, plot generation, and parameterizing the convolutional neural network trained.
:return dictionary that holds all the information for the finished model.
'''
# data_path = get_folder_dir()
logger("Generating datasets for classes")
if pretrained:
if not height:
height = 224
if not width:
width = 224
if height != 224 or width != 224:
raise ValueError(
"For pretrained models, both 'height' and 'width' must be 224."
)
if preprocess:
if custom_arch:
raise ValueError(
"If 'custom_arch' is not None, 'preprocess' must be set to false."
)
read_mode_info = set_distinguisher(data_path, read_mode)
read_mode = read_mode_info["read_mode"]
training_path = "/proc_training_set"
testing_path = "/proc_testing_set"
if read_mode == "setwise":
processInfo = setwise_preprocessing(data_path, new_folders, height,
width)
if not new_folders:
training_path = "/training_set"
testing_path = "/testing_set"
# if image dataset in form of csv
elif read_mode == "csvwise":
if training_ratio <= 0 or training_ratio >= 1:
raise BaseException(f"Test ratio must be between 0 and 1.")
processInfo = csv_preprocessing(read_mode_info["csv_path"],
data_path, instruction,
image_column, training_ratio,
height, width)
# if image dataset in form of one folder containing class folders
elif read_mode == "classwise":
if training_ratio <= 0 or training_ratio >= 1:
raise BaseException(f"Test ratio must be between 0 and 1.")
processInfo = classwise_preprocessing(data_path, training_ratio,
height, width)
else:
training_path = "/training_set"
testing_path = "/testing_set"
processInfo = already_processed(data_path)
num_channels = 3
color_mode = 'rgb'
if processInfo["gray_scale"]:
num_channels = 1
color_mode = 'grayscale'
input_shape = (processInfo["height"], processInfo["width"], num_channels)
input_single = (processInfo["height"], processInfo["width"])
num_classes = processInfo["num_categories"]
loss_func = ""
output_layer_activation = ""
if num_classes > 2:
loss_func = "categorical_crossentropy"
output_layer_activation = "softmax"
elif num_classes == 2:
num_classes = 1
loss_func = "binary_crossentropy"
output_layer_activation = "sigmoid"
logger("Creating convolutional neural netwwork dynamically")
# Convolutional Neural Network
# Build model based on custom_arch configuration if given
if custom_arch:
with open(custom_arch, "r") as f:
custom_arch_dict = json.load(f)
custom_arch_json_string = json.dumps(custom_arch_dict)
model = model_from_json(custom_arch_json_string)
# Build an existing state-of-the-art model
elif pretrained:
arch_lower = pretrained.get('arch').lower()
# If user specifies value of pretrained['weights'] as 'imagenet', weights pretrained on ImageNet will be used
if 'weights' in pretrained and pretrained.get('weights') == 'imagenet':
# Load ImageNet pretrained weights
if arch_lower == "vggnet16":
base_model = VGG16(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = Flatten()(base_model.output)
x = Dense(4096)(x)
x = Dropout(0.5)(x)
x = Dense(4096)(x)
x = Dropout(0.5)(x)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "vggnet19":
base_model = VGG19(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = Flatten()(base_model.output)
x = Dense(4096)(x)
x = Dropout(0.5)(x)
x = Dense(4096)(x)
x = Dropout(0.5)(x)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "resnet50":
base_model = ResNet50(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = Flatten()(base_model.output)
x = GlobalAveragePooling2D()(base_model.output)
x = Dropout(0.5)(x)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "resnet101":
base_model = ResNet101(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = GlobalAveragePooling2D()(base_model.output)
x = Dropout(0.5)(x)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "resnet152":
base_model = ResNet152(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = GlobalAveragePooling2D()(base_model.output)
x = Dropout(0.5)(x)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
else:
raise ModuleNotFoundError("arch \'" + pretrained.get('arch') +
"\' not supported.")
else:
# Randomly initialized weights
if arch_lower == "vggnet16":
model = VGG16(include_top=True,
weights=None,
classes=num_classes,
classifier_activation=output_layer_activation)
elif arch_lower == "vggnet19":
model = VGG19(include_top=True,
weights=None,
classes=num_classes,
classifier_activation=output_layer_activation)
elif arch_lower == "resnet50":
model = ResNet50(include_top=True,
weights=None,
classes=num_classes)
elif arch_lower == "resnet101":
model = ResNet101(include_top=True,
weights=None,
classes=num_classes)
elif arch_lower == "resnet152":
model = ResNet152(include_top=True,
weights=None,
classes=num_classes)
else:
raise ModuleNotFoundError("arch \'" + pretrained.get('arch') +
"\' not supported.")
else:
model = Sequential()
# model.add(
# Conv2D(
# 64,
# kernel_size=3,
# activation="relu",
# input_shape=input_shape))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Conv2D(64, kernel_size=3, activation="relu"))
# model.add(MaxPooling2D(pool_size=(2, 2)))
# model.add(Flatten())
# model.add(Dense(num_classes, activation="softmax"))
# model.compile(
# optimizer="adam",
# loss=loss_func,
# metrics=['accuracy'])
model.add(
Conv2D(filters=64,
kernel_size=5,
activation="relu",
input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(filters=64, kernel_size=3, activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Conv2D(filters=64, kernel_size=3, activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(units=256, activation="relu"))
model.add(Dropout(0.25))
model.add(Dense(units=num_classes, activation="softmax"))
model.compile(optimizer="adam", loss=loss_func, metrics=['accuracy'])
logger("Located image data")
if augmentation:
train_data = ImageDataGenerator(rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_data = ImageDataGenerator(rescale=1. / 255)
logger('Dataset augmented through zoom, shear, flip, and rescale')
else:
train_data = ImageDataGenerator()
test_data = ImageDataGenerator()
logger("->", "Optimal image size identified: {}".format(input_shape))
X_train = train_data.flow_from_directory(
data_path + training_path,
target_size=input_single,
color_mode=color_mode,
batch_size=(16 if processInfo["train_size"] >= 16 else 1),
class_mode=loss_func[:loss_func.find("_")])
X_test = test_data.flow_from_directory(
data_path + testing_path,
target_size=input_single,
color_mode=color_mode,
batch_size=(16 if processInfo["test_size"] >= 16 else 1),
class_mode=loss_func[:loss_func.find("_")])
if epochs <= 0:
raise BaseException("Number of epochs has to be greater than 0.")
logger('Training image model')
history = model.fit_generator(
X_train,
steps_per_epoch=X_train.n // X_train.batch_size,
validation_data=X_test,
validation_steps=X_test.n // X_test.batch_size,
epochs=epochs,
verbose=verbose)
logger(
'->', 'Final training accuracy: {}'.format(
history.history['accuracy'][len(history.history['accuracy']) - 1]))
logger(
'->',
'Final validation accuracy: {}'.format(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1]))
# storing values the model dictionary
logger("Stored model under 'convolutional_NN' key")
clearLog()
return {
'id': generate_id(),
'data_type': read_mode,
'data_path': data_path,
'data': {
'train': X_train,
'test': X_test
},
'shape': input_shape,
"model": model,
'losses': {
'training_loss': history.history['loss'],
'val_loss': history.history['val_loss']
},
'accuracy': {
'training_accuracy': history.history['accuracy'],
'validation_accuracy': history.history['val_accuracy']
},
'num_classes': (2 if num_classes == 1 else num_classes),
'data_sizes': {
'train_size': processInfo['train_size'],
'test_size': processInfo['test_size']
}
}
def convolutional(instruction=None,
read_mode=None,
text=None,
data_path=os.getcwd(),
new_folders=True,
image_column=None,
training_ratio=0.8,
augmentation=True):
logger("Generating datasets for classes...")
read_mode_info = set_distinguisher(data_path, read_mode)
read_mode = read_mode_info["read_mode"]
training_path = "/proc_training_set"
testing_path = "/proc_testing_set"
if read_mode == "setwise":
processInfo = setwise_preprocessing(data_path, new_folders)
if not new_folders:
training_path = "/training_set"
testing_path = "/testing_set"
# if image dataset in form of csv
elif read_mode == "pathwise or namewise":
processInfo = csv_preprocessing(read_mode_info["csv_path"], data_path,
instruction, image_column,
training_ratio)
# if image dataset in form of one folder containing class folders
elif read_mode == "classwise":
processInfo = classwise_preprocessing(data_path, training_ratio)
input_shape = (processInfo["height"], processInfo["width"], 3)
input_single = (processInfo["height"], processInfo["width"])
num_classes = processInfo["num_categories"]
loss_func = ""
if num_classes > 2:
loss_func = "categorical_crossentropy"
elif num_classes == 2:
loss_func = "binary_crossentropy"
logger("Creating convolutional neural network dynamically...")
# Convolutional Neural Network
model = Sequential()
model.add(
Conv2D(64, kernel_size=3, activation="relu", input_shape=input_shape))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, kernel_size=3, activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(num_classes, activation="softmax"))
model.compile(optimizer="adam", loss=loss_func, metrics=['accuracy'])
if augmentation:
train_data = ImageDataGenerator(rescale=1. / 255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_data = ImageDataGenerator(rescale=1. / 255)
else:
train_data = ImageDataGenerator()
test_data = ImageDataGenerator()
"""
trainingImages = []
train_labels = []
validationImages = []
test_labels = []
for path in imgPaths:
classLabel = path.split(os.path.sep)[-2]
classes.add(classLabel)
img = img_to_array(load_img(path, target_size=(64, 64)))
if path.split(os.path.sep)[-3] == 'training_set':
trainingImages.append(img)
train_labels.append(classLabel)
else:
validationImages.append(img)
test_labels.append(classLabel)
trainingImages = np.array(trainingImages)
train_labels = to_categorical(np.array(train_labels))
validationImages = np.array(validationImages)
test_labels = to_categorical(np.array(test_labels))
model.compile(loss=’categorical_crossentropy’,
optimizer=’sgd’,
metrics=[‘accuracy’])
history=model.fit(train_images, train_labels,
batch_size=100,
epochs=5,
verbose=1)
"""
X_train = train_data.flow_from_directory(
data_path + training_path,
target_size=input_single,
color_mode='rgb',
batch_size=(32 if processInfo["train_size"] >= 32 else 1),
class_mode=loss_func[:loss_func.find("_")])
X_test = test_data.flow_from_directory(
data_path + testing_path,
target_size=input_single,
color_mode='rgb',
batch_size=(32 if processInfo["test_size"] >= 32 else 1),
class_mode=loss_func[:loss_func.find("_")])
# print(X_train)
history = model.fit(X_train,
steps_per_epoch=X_train.n // X_train.batch_size,
validation_data=X_test,
validation_steps=X_test.n // X_test.batch_size,
epochs=1)
# storing values the model dictionary
return {
'id': generate_id(),
"model": model,
'num_classes': (2 if num_classes == 1 else num_classes),
'losses': {
'training_loss': history.history['loss'],
'val_loss': history.history['val_loss']
},
'accuracy': {
'training_accuracy': history.history['accuracy'],
'validation_accuracy': history.history['val_accuracy']
}
}
