def model_builder(numhiddenlayers=3, init_mode='uniform', neurons=[400, 300, 200, 100, 50, 200, 200], acti='relu'):
Model = Sequential()
Model.add(Dense(neurons[0], input_shape=(DOF,), kernel_initializer=init_mode, activation=acti))
for i in range(0, numhiddenlayers):
Model.add(Dense(neurons[i + 1], kernel_initializer=init_mode, activation=acti))
Model.add(Dense(POSOR))
return Model
def convolutional(instruction=None,
read_mode=None,
preprocess=True,
data_path=None,
verbose=0,
new_folders=True,
image_column=None,
training_ratio=0.8,
fine_tune=False,
augmentation=True,
custom_arch=None,
pretrained=None,
epochs=10,
height=None,
width=None,
save_as_tfjs=None,
save_as_tflite=None,
generate_plots=True):
'''
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")
LR = 0.001
plots = {}
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 network 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)
elif arch_lower == "mobilenet":
base_model = MobileNet(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = fine_tuned_model(base_model)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "mobilenetv2":
base_model = MobileNetV2(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = fine_tuned_model(base_model)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "densenet121":
base_model = DenseNet121(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = fine_tuned_model(base_model)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "densenet169":
base_model = DenseNet169(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = fine_tuned_model(base_model)
pred = Dense(num_classes,
activation=output_layer_activation)(x)
model = Model(base_model.input, pred)
elif arch_lower == "densenet201":
base_model = DenseNet201(include_top=False,
weights='imagenet',
input_shape=input_shape)
x = fine_tuned_model(base_model)
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)
elif arch_lower == "mobilenet":
model = MobileNet(include_top=True,
weights=None,
classes=num_classes)
elif arch_lower == "mobilenetv2":
model = MobileNetV2(include_top=True,
weights=None,
classes=num_classes)
elif arch_lower == "densenet121":
model = DenseNet121(include_top=True,
weights=None,
classes=num_classes)
elif arch_lower == "densenet169":
model = DenseNet169(include_top=True,
weights=None,
classes=num_classes)
elif arch_lower == "densenet201":
model = DenseNet201(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"))
if pretrained and 'weights' in pretrained and pretrained.get(
'weights') == 'imagenet':
for layer in base_model.layers:
layer.trainable = False
opt = Adam(learning_rate=LR)
model.compile(optimizer=opt, 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.")
print("\n")
logger('Training image model')
# model.summary()
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)
if fine_tune:
logger(
'->', 'Training accuracy: {}'.format(
history.history['accuracy'][len(history.history['accuracy']) -
1]))
logger(
'->',
'Validation accuracy: {}'.format(history.history['val_accuracy'][
len(history.history['val_accuracy']) - 1]))
for layer in base_model.layers:
layer.trainable = True
opt = Adam(learning_rate=LR / 10)
model.compile(optimizer=opt, loss=loss_func, metrics=['accuracy'])
print("\n\n")
logger('Training fine tuned model')
fine_tuning_epoch = epochs + 10
history_fine = 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=fine_tuning_epoch,
initial_epoch=history.epoch[-1],
verbose=verbose)
#frozen model acc and loss history
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']
#fine tuned model acc and loss history
acc += history_fine.history['accuracy']
val_acc += history_fine.history['val_accuracy']
loss += history_fine.history['loss']
val_loss += history_fine.history['val_loss']
if generate_plots:
plots = generate_fine_tuned_classification_plots(
acc, val_acc, loss, val_loss, epochs)
models = []
losses = []
accuracies = []
model_data = []
model_data.append(model)
models.append(history)
losses.append(
history.history["val_loss"][len(history.history["val_loss"]) - 1])
accuracies.append(
history.history['val_accuracy'][len(history.history['val_accuracy']) -
1])
# final_model = model_data[accuracies.index(max(accuracies))]
# final_hist = models[accuracies.index(max(accuracies))]
if generate_plots and not fine_tune:
plots = generate_classification_plots(models[len(models) - 1])
print("\n")
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
number_of_examples = len(X_test.filenames)
number_of_generator_calls = math.ceil(number_of_examples /
(1.0 * X_test.batch_size))
test_labels = []
for i in range(0, int(number_of_generator_calls)):
test_labels.extend(np.array(X_test[i][1]))
predIdx = model.predict(X_test)
if output_layer_activation == "sigmoid":
real = [int(x) for x in test_labels]
ans = []
for i in range(len(predIdx)):
ans.append(int(round(predIdx[i][0])))
elif output_layer_activation == "softmax":
real = []
for ans in test_labels:
real.append(ans.argmax())
ans = []
for r in predIdx:
ans.append(r.argmax())
else:
print("NOT THE CASE")
logger("Stored model under 'convolutional_NN' key")
if save_as_tfjs:
tfjs.converters.save_keras_model(model, "tfjsmodel")
logger("Saved tfjs model under 'tfjsmodel' directory")
if save_as_tflite:
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()
open("model.tflite", "wb").write(tflite_model)
logger("Saved tflite model as 'model.tflite' ")
clearLog()
K.clear_session()
return {
'id': generate_id(),
'data_type': read_mode,
'data_path': data_path,
'data': {
'train': X_train,
'test': X_test
},
'shape': input_shape,
'res': {
'real': real,
'ans': ans
},
'model': model,
'plots': plots,
'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 model_builder():
Model = Sequential()
Model.add(
Dense(500,
input_shape=(4, ),
kernel_initializer="uniform",
activation="sigmoid"))
Model.add(Dense(500, kernel_initializer="uniform", activation="sigmoid"))
Model.add(Dense(400, kernel_initializer="uniform", activation="sigmoid"))
Model.add(Dense(400, kernel_initializer="uniform", activation="sigmoid"))
Model.add(Dense(300, kernel_initializer="uniform", activation="sigmoid"))
Model.add(Dense(3))
return Model
def create_model(**kwargs):
# verbose
verbose = kwargs.pop('verbose', False)
# input shape
img_width = kwargs.pop('img_width', 250)
img_height = kwargs.pop('img_height', 250)
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)
# base model class + frozen layers
base_model_class = kwargs.pop('base_model_class', None)
tune_layers = kwargs.pop('tune_layers', None)
if base_model_class:
base_model = base_model_class(include_top=False,
input_shape=input_shape)
if tune_layers:
for layer in base_model.layers[:-tune_layers]:
layer.trainable = False
# print(base_model.summary())
# classes (binary or multclass)
no_classes = kwargs.pop('no_classes', 120)
if no_classes == 2:
final_activation = 'sigmoid'
no_classes = 1 # binary classficication
else:
final_activation = 'softmax'
# model
if base_model_class:
top_model = Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
top_model.add(Dense(256))
top_model.add(Activation('relu'))
top_model.add(Dropout(0.3))
# final layer
top_model.add(Dense(no_classes))
top_model.add(Activation(final_activation))
model = Model(inputs=base_model.input,
outputs=top_model(base_model.output))
else:
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
# final layer
model.add(Dense(no_classes))
model.add(Activation(final_activation))
# list of metrics
metric_list = kwargs.pop('metric_list', [])
# optimizer
optimizer_class = kwargs.pop('optimizer_class', optimizers.Adam)
optimizer_kwargs = kwargs.pop('optimizer_kwargs', {})
optimizer = optimizer_class(**optimizer_kwargs)
# loss
if no_classes <= 2:
default_loss = 'binary_crossentropy'
else:
default_loss = 'categorical_crossentropy'
loss = kwargs.pop('loss', default_loss)
# compile model
model.compile(loss=loss, optimizer=optimizer, metrics=metric_list)
if verbose:
# not so nice
print('base_model is {}'.format(base_model.summary()))
print('top_model is {}'.format(top_model.summary()))
print('complete model is {}'.format(model.summary()))
return model
x = Dropout(0.25)(x) x = Conv2D(64,(3,3),padding='same',activation='relu')(x) x = Conv2D(64,(3,3),activation='relu')(x) x = MaxPooling2D(pool_size=(2, 2))(x) x = Dropout(0.25)(x) x = Flatten()(x) x = Dense(512,activation='relu')(x) x = Dropout(0.5)(x) x = Dense(10,activation='softmax')(x) model = Model(input=inputs,output=x) #/----------------------------method1-API方法----------------------------- #/----------------------------method2-Sequential方法---------------------- model = Sequential() model.add(Conv2D(32,(3,3),padding='same',input_shape=x_train.shape[1:],activation='relu'))#第一层需要指出输入图像的大小 model.add(Conv2D(32,(3,3),activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25)) model.add(Conv2D(64,(3,3),padding='same',activation='relu')) model.add(Conv2D(64,(3,3),activation='relu')) model.add(MaxPooling2D(pool_size=(2, 2))) model.add(Dropout(0.25)) model.add(Flatten()) model.add(Dense(512)) model.add(activation='relu') model.add(Dropout(0.5)) model.add(Dense(10)) model.add(activation='softmax')
