如何在 Keras 中为 VGG16 微调预处理训练集？

Question

我已经微调了 Keras VGG16 模型，但我不确定训练阶段的预处理。

我创建了一个火车生成器，如下所示：

train_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
        train_folder,
        target_size=(IMAGE_SIZE, IMAGE_SIZE),
        batch_size=train_batchsize,
        class_mode="categorical"
    )

重新缩放是否足够，或者我必须应用其他预处理功能？

当我使用网络对图像进行分类时，我使用以下代码：

from keras.models import load_model
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np

img = image.load_img(img_path, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
preds = model.predict(x)

我认为这是正确的预处理，我应该在训练前应用它。

谢谢你的帮助。

Answer 1

ImageDataGenerator 有一个preprocessing_function参数，它允许您传递preprocess_input在推理过程中使用的相同函数。此函数将为您进行重新缩放，因此可以省略缩放：

from keras.applications.vgg16 import preprocess_input
train_datagen = ImageDataGenerator(preprocessing_function=preprocess_input)

keras_applications 中的大部分预训练模型都使用相同的预处理函数。您可以检查文档字符串以查看它的作用：

def preprocess_input(x, data_format=None, mode='caffe', **kwargs):
    """Preprocesses a tensor or Numpy array encoding a batch of images.
    # Arguments
        x: Input Numpy or symbolic tensor, 3D or 4D.
            The preprocessed data is written over the input data
            if the data types are compatible. To avoid this
            behaviour, `numpy.copy(x)` can be used.
        data_format: Data format of the image tensor/array.
        mode: One of "caffe", "tf" or "torch".
            - caffe: will convert the images from RGB to BGR,
                then will zero-center each color channel with
                respect to the ImageNet dataset,
                without scaling.
            - tf: will scale pixels between -1 and 1,
                sample-wise.
            - torch: will scale pixels between 0 and 1 and then
                will normalize each channel with respect to the
                ImageNet dataset.
    # Returns
        Preprocessed tensor or Numpy array.