tensorflow - 结合两个数据生成器来训练一个 CNN

您已将所有数据分成两个不同的目录；现在你想用这两个目录中的数据训练模型。

您可以通过两种方式实现此目的：

Keras ImageDataGeneratorflow_from_directory方法有一个follow_links参数。您可以使用follow_links. 根据您的需要和所需的类结构创建一个单独的目录。在其中，从您的原始数据目录创建符号链接。在下图中，您可以使用该data目录作为主要输入目录。

.
├── Directory1/
│   ├── Class1/
│   └── Class2/
├── Directory2/
│   ├── Class1/
│   └── Class2/
└── Data/
    ├── Class1/
    │   ├── symlink_to_Directory1_Class1
    │   └── symlink_to_Directory2_Class1
    └── Class2/
        ├── symlink_to_Directory1_Class2
        └── symlink_to_Directory2_Class2

为两个不同的目录制作ImageDatagenerator 了两个不同的目录。然后将它们合并为一个。在这种情况下，子生成器的批量大小必须与各个目录中的数据数量成比例地确定。

子生成器的批量大小： $b = \frac{B \times n}{\sum{n}}$

Where,
b = Batch Size Of Any Sub-generator
B = Desired Batch Size Of The Merged Generator
n = Number Of Images In That Directory Of Sub-generator
the sum of n = Total Number Of Images In All Directories

请参阅下面的代码

from keras.preprocessing.image import ImageDataGenerator
from keras.utils import Sequence
import matplotlib.pyplot as plt
import numpy as np
import os


class MergedGenerators(Sequence):

    def __init__(self, batch_size, generators=[], sub_batch_size=[]):
        self.generators = generators
        self.sub_batch_size = sub_batch_size
        self.batch_size = batch_size

    def __len__(self):
        return int(
            sum([(len(self.generators[idx]) * self.sub_batch_size[idx])
                 for idx in range(len(self.sub_batch_size))]) /
            self.batch_size)

    def __getitem__(self, index):
        """Getting items from the generators and packing them"""

        X_batch = []
        Y_batch = []
        for generator in self.generators:
            if generator.class_mode is None:
                x1 = generator[index % len(generator)]
                X_batch = [*X_batch, *x1]

            else:
                x1, y1 = generator[index % len(generator)]
                X_batch = [*X_batch, *x1]
                Y_batch = [*Y_batch, *y1]

        if self.generators[0].class_mode is None:
            return np.array(X_batch)
        return np.array(X_batch), np.array(Y_batch)


def build_datagenerator(dir1=None, dir2=None, batch_size=32):
    n_images_in_dir1 = sum([len(files) for r, d, files in os.walk(dir1)])
    n_images_in_dir2 = sum([len(files) for r, d, files in os.walk(dir2)])

    # Have to set different batch size for two generators as number of images
    # in those two directories are not same. As we have to equalize the image
    # share in the generators
    generator1_batch_size = int((n_images_in_dir1 * batch_size) /
                                (n_images_in_dir1 + n_images_in_dir2))

    generator2_batch_size = batch_size - generator1_batch_size

    generator1 = ImageDataGenerator(
        rescale=1. / 255,
        shear_range=0.2,
        zoom_range=0.2,
        rotation_range=5.,
        horizontal_flip=True,
    )

    generator2 = ImageDataGenerator(
        rescale=1. / 255,
        zoom_range=0.2,
        horizontal_flip=False,
    )

    # generator2 has different image augmentation attributes than generaor1
    generator1 = generator1.flow_from_directory(
        dir1,
        target_size=(128, 128),
        color_mode='rgb',
        class_mode=None,
        batch_size=generator1_batch_size,
        shuffle=True,
        seed=42,
        interpolation="bicubic",
    )

    generator2 = generator2.flow_from_directory(
        dir2,
        target_size=(128, 128),
        color_mode='rgb',
        class_mode=None,
        batch_size=generator2_batch_size,
        shuffle=True,
        seed=42,
        interpolation="bicubic",
    )

    return MergedGenerators(
        batch_size,
        generators=[generator1, generator2],
        sub_batch_size=[generator1_batch_size, generator2_batch_size])


def test_datagen(batch_size=32):
    datagen = build_datagenerator(dir1="./asdf",
                                  dir2="./asdf2",
                                  batch_size=batch_size)

    print("Datagenerator length (Batch count):", len(datagen))

    for batch_count, image_batch in enumerate(datagen):
        if batch_count == 1:
            break

        print("Images: ", image_batch.shape)

        plt.figure(figsize=(10, 10))
        for i in range(image_batch.shape[0]):
            plt.subplot(1, batch_size, i + 1)
            plt.imshow(image_batch[i], interpolation='nearest')
            plt.axis('off')
            plt.tight_layout()


test_datagen(4)

tensorflow - 结合两个数据生成器来训练一个 CNN

问题描述

解决方案

推荐阅读