def tune(lr=0.0001, class_weight=None):
model = load_model(nb_class=len(config.classes), weights_path=config.get_top_model_weights_path())
model.compile(
loss='categorical_crossentropy',
optimizer=SGD(lr=lr, decay=1e-6, momentum=0.9, nesterov=True),
metrics=['accuracy'])
# prepare data augmentation configuration
train_datagen = ImageDataGenerator(
rotation_range=30.,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
util.apply_mean(train_datagen)
train_generator = train_datagen.flow_from_directory(
config.train_dir,
target_size=config.img_size,
classes=config.classes)
test_datagen = ImageDataGenerator()
util.apply_mean(test_datagen)
validation_generator = test_datagen.flow_from_directory(
config.validation_dir,
target_size=config.img_size,
classes=config.classes)
early_stopping = EarlyStopping(verbose=1, patience=30, monitor='val_loss')
model_checkpoint = ModelCheckpoint(config.get_fine_tuned_weights_path(checkpoint=True),
save_best_only=True,
save_weights_only=True,
monitor='val_loss')
history = model.fit_generator(
train_generator,
samples_per_epoch=config.nb_train_samples,
nb_epoch=fine_tuning_nb_epoch,
validation_data=validation_generator,
nb_val_samples=config.nb_validation_samples,
callbacks=[early_stopping, model_checkpoint],
class_weight=class_weight)
util.save_history(history=history, prefix='fine-tuning')
util.save_classes(config.classes)
_cleanup()
def _get_data_generators(train_datagen):
util.apply_mean(train_datagen)
train_generator = train_datagen.flow_from_directory(
config.train_dir,
target_size=config.img_size,
classes=config.classes,
shuffle=False)
test_datagen = ImageDataGenerator()
util.apply_mean(test_datagen)
validation_generator = test_datagen.flow_from_directory(
config.validation_dir,
target_size=config.img_size,
classes=config.classes,
shuffle=False)
return train_generator, validation_generator
def save_bottleneck_features():
model = VGG16(weights='imagenet', include_top=False)
datagen = ImageDataGenerator()
util.apply_mean(datagen)
generator = datagen.flow_from_directory(config.train_dir,
target_size=config.img_size,
shuffle=False,
classes=config.classes)
bottleneck_features_train = model.predict_generator(
generator, config.nb_train_samples)
np.save(open(config.bf_train_path, 'w'), bottleneck_features_train)
generator = datagen.flow_from_directory(config.validation_dir,
target_size=config.img_size,
shuffle=False,
classes=config.classes)
bottleneck_features_validation = model.predict_generator(
generator, config.nb_validation_samples)
np.save(open(config.bf_valid_path, 'w'), bottleneck_features_validation)