tf.data.Dataset 来自 tf.keras.preprocessing.image.ImageDataGenerator.flow_from_directory？

Question

如何创建 tf.data.Dataset from tf.keras.preprocessing.image.ImageDataGenerator.flow_from_directory？

我正在考虑 tf.data.Dataset.from_generator，但不清楚如何为其获取 output_types 关键字参数，给定 return 类型：

A DirectoryIterator yielding tuples of (x, y) where x is a numpy array containing a batch of images with shape (batch_size, *target_size, channels) and y is a numpy array of corresponding labels.

Answer 1

ImageDataGenerator中的两个batch_x and batch_y都是K.floatx()类型，所以默认必须是tf.float32。

How to use Keras generator with tf.data API 已经讨论过类似的问题。让我从那里复制粘贴答案：

def make_generator():
    train_datagen = ImageDataGenerator(rescale=1. / 255)
    train_generator = 
    train_datagen.flow_from_directory(train_dataset_folder,target_size=(224, 224), class_mode='categorical', batch_size=32)
    return train_generator

train_dataset = tf.data.Dataset.from_generator(make_generator,(tf.float32, tf.float32))

作者遇到了另一个图形范围问题，但我想这与您的问题无关。

或作为一个班轮：

tf.data.Dataset.from_generator(lambda:
    ImageDataGenerator().flow_from_directory('folder_path'),(tf.float32, tf.float32))

Answer 2

这是我的解决方案。为了展示它是如何工作的，我使用 cats/dogs 数据集：

import matplotlib.pyplot as plt
import numpy as np
import os
import tensorflow as tf


_URL = 'https://storage.googleapis.com/mledu-datasets/cats_and_dogs_filtered.zip'
path_to_zip = tf.keras.utils.get_file('cats_and_dogs.zip', origin=_URL, extract=True)
PATH = os.path.join(os.path.dirname(path_to_zip), 'cats_and_dogs_filtered')

train_dir = os.path.join(PATH, 'train')
#'/Users/mustafamuratarat/.keras/datasets/cats_and_dogs_filtered/train'

BATCH_SIZE = 32
IMG_SIZE = (160, 160)

img_gen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)

gen = img_gen.flow_from_directory(train_dir, target_size=(160, 160), batch_size=32)
#<tensorflow.python.keras.preprocessing.image.DirectoryIterator at 0x7fb9fde3b250>

#gen.class_indices
#{'cats': 0, 'dogs': 1}

#gen.target_size
#(160, 160)

# gen.batch_size
# 32

# gen.num_classes
# 2

dataset = tf.data.Dataset.from_generator(
    lambda: gen,
    output_types = (tf.float32, tf.float32),
    output_shapes = ([None, 160, 160, 3], [None, 2]),
)

#list(dataset.take(1).as_numpy_iterator())

然后您可以将 dataset 对象提供给任何模型。

tf.data.Dataset 来自 tf.keras.preprocessing.image.ImageDataGenerator.flow_from_directory？

tf.data.Dataset from tf.keras.preprocessing.image.ImageDataGenerator.flow_from_directory?

python

numpy

marshalling

keras

tensorflow