Keras：使用flow_from_directory为fit_generator输入多个输入

Question

是否可以在fit_generator中有两个flow_from_directory？

例如

train_generator_1 = train_datagen.flow_from_directory(
    train_data_dir_1,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary')

train_generator_2 = train_datagen.flow_from_directory(
    train_data_dir_2,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary')

custom_vgg_model.fit_generator(
    [train_generator_1, train_generator_2],
    steps_per_epoch=nb_train_samples,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples,
    callbacks=[checkpointer, csv_logger])

Answer 1

您可以尝试制作包含以下内容的生成器：

在python 3中：

def doubleGenerator(generator1,generator2):

    while True:
        for (x1,y1),(x2,y2) in zip(generator1,generator2):
            yield ([x1,x2],y1)