Keras:使用flow_from_directory的fit_generator的多个输入 [英] Keras: Multiple Inputs for fit_generator using flow_from_directory

问题描述

fit_generator中是否可以有两个flow_from_directory?

Is it possible to have two flow_from_directory in a fit_generator?

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])

推荐答案

您可以尝试制作一个同时包含这两者的生成器:

You can try making a generator that contains both:

在python 3中:

In python 3:

def doubleGenerator(generator1,generator2):

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

这篇关于Keras:使用flow_from_directory的fit_generator的多个输入的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！