以fine-tuning Keras中的Resnet50模型为例。例如,在这里:
from keras.applications.resnet50 import ResNet50
from keras.preprocessing import image
from keras.preprocessing.image import ImageDataGenerator
from keras.applications.resnet50 import preprocess_input, decode_predictions
import numpy as np
model = ResNet50(weights='imagenet')
train_datagen = ImageDataGenerator()
train_generator = train_datagen.flow_from_directory(
"./data/train",
target_size=(299, 299),
batch_size=50,
class_mode='binary')
model.fit_generator(train_generator, steps_per_epoch=100)
我感到困惑的是为什么ImageDataGenerator没有给出与Resnet50期望相一致的
preprocessing_function
规范。具体来说,Resnet50.preprocess_input()
被提供在ResNet50软件包中。而ImageDataGenerator
的输入如下:keras.preprocessing.image.ImageDataGenerator(featurewise_center=False,
samplewise_center=False,
featurewise_std_normalization=False,
samplewise_std_normalization=False,
zca_whitening=False,
zca_epsilon=1e-6,
rotation_range=0.,
width_shift_range=0.,
height_shift_range=0.,
shear_range=0.,
zoom_range=0.,
channel_shift_range=0.,
fill_mode='nearest',
cval=0.,
horizontal_flip=False,
vertical_flip=False,
rescale=None,
preprocessing_function=None,
data_format=K.image_data_format())
所以我对ImageDataGenerator的正确初始化感到困惑。我可以设置
preprocessing_function=resnet50.Resnet50.preprocess_input
,但是我不确定其余的ImageDataGenerator参数应该设置什么,因为其中一些是非零的,比如zca。注意:我不仅对Resnet50感兴趣,而是对所有模型都感兴趣。在Keras中似乎有一些默认值,例如默认为“caffe”或“inception”归一化。