在 keras 中创建混合数据生成器（图像、csv）

Question

我正在构建一个具有多个输入的模型，如 pyimagesearch 所示，但是我无法将所有图像加载到 RAM 中，我正在尝试创建一个使用 flow_from_directory 并从 CSV 文件中获取所有额外内容的生成器每个正在处理的图像的属性。

问题：如何从 CSV 中获取属性以与图像生成器中每批中的图像相对应？

def get_combined_generator(images_dir, csv_dir, split, *args):
    """
    Creates train/val generators on images and csv data.

    Arguments:

    images_dir : string
        Path to a directory with subdirectories for each class.

    csv_dir : string
        Path to a directory containing train/val csv files with extra attributes.

    split : string
        Current split being used (train, val or test)
    """
    img_width, img_height, batch_size = args

    datagen = ImageDataGenerator(
        rescale=1. / 255)

    generator = datagen.flow_from_directory(
        f'{images_dir}/{split}',
        target_size=(img_width, img_height),
        batch_size=batch_size,
        shuffle=True,
        class_mode='categorical')

    df = pd.read_csv(f'{csv_dir}/{split}.csv', index_col='image')

    def my_generator(image_gen, data):
        while True:
            i = image_gen.batch_index
            batch = image_gen.batch_size
            row = data[i * batch:(i + 1) * batch]
            images, labels = image_gen.next()
            yield [images, row], labels

    csv_generator = my_generator(generator, df)

    return csv_generator

Answer 1

鉴于这种相对具体的情况，我建议创建一个自定义生成器。类似以下的内容（从类似的答案 here 修改）就足够了：

import os
import random
import pandas as pd

def generator(image_dir, csv_dir, batch_size):
    i = 0
    image_file_list = os.listdir(image_dir)
    while True:
        batch_x = {'images': list(), 'other_feats': list()}  # use a dict for multiple inputs
        batch_y = list()
        for b in range(batch_size):
            if i == len(image_file_list):
                i = 0
                random.shuffle(image_file_list)
            sample = image_file_list[i]
            image_file_path = sample[0]
            csv_file_path = os.path.join(csv_dir,
                                         os.path.basename(image_file_path).replace('.png', '.csv'))
            i += 1
            image = preprocess_image(cv2.imread(image_file_path))
            csv_file = pd.read_csv(csv_file_path)
            other_feat = preprocess_feats(csv_file)
            batch_x['images'].append(image)
            batch_x['other_feats'].append(other_feat)
            batch_y.append(csv_file.loc[image_name, :]['class'])

        batch_x['images'] = np.array(batch_x['images'])  # convert each list to array
        batch_x['other_feats'] = np.array(batch_x['other_feats'])
        batch_y = np.eye(num_classes)[batch['labels']]
        yield batch_x, batch_y

然后，您可以使用 Keras 的 fit_generator() 函数来训练您的模型。

显然，这假设您有与图像文件同名的csv 文件，并且您有一些用于图像和csv 文件的自定义preprocessing 函数。

Answer 2

我使用自定义生成器根据 Luke 的回答找到了解决方案

import random
import pandas as pd
import numpy as np
from glob import glob
from keras.preprocessing import image as krs_image

# Create the arguments for image preprocessing
data_gen_args = dict(
    horizontal_flip=True,
    brightness_range=[0.5, 1.5],
    shear_range=10,
    channel_shift_range=50,
    rescale=1. / 255,
)

# Create an empty data generator
datagen = ImageDataGenerator()

# Read the image list and csv
image_file_list = glob(f'{images_dir}/{split}/**/*.JPG', recursive=True)
df = pd.read_csv(f'{csv_dir}/{split}.csv', index_col=csv_data[0])
random.shuffle(image_file_list)

def custom_generator(images_list, dataframe, batch_size):
    i = 0
    while True:
        batch = {'images': [], 'csv': [], 'labels': []}
        for b in range(batch_size):
            if i == len(images_list):
                i = 0
                random.shuffle(images_list)
            # Read image from list and convert to array
            image_path = images_list[i]
            image_name = os.path.basename(image_path).replace('.JPG', '')
            image = krs_image.load_img(image_path, target_size=(img_height, img_width))
            image = datagen.apply_transform(image, data_gen_args)
            image = krs_image.img_to_array(image)

            # Read data from csv using the name of current image
            csv_row = dataframe.loc[image_name, :]
            label = csv_row['class']
            csv_features = csv_row.drop(labels='class')

            batch['images'].append(image)
            batch['csv'].append(csv_features)
            batch['labels'].append(label)

            i += 1

        batch['images'] = np.array(batch['images'])
        batch['csv'] = np.array(batch['csv'])
        # Convert labels to categorical values
        batch['labels'] = np.eye(num_classes)[batch['labels']]

        yield [batch['images'], batch['csv']], batch['labels']