带有Keras错误的多分类NN [英] Multi-Classification NN with Keras error

问题描述

尝试对三个类进行多分类时出现错误.

I am getting an error when trying to do multi-classification with three classes.

Error: TypeError: fit_generator() got multiple values for argument 'steps_per_epoch'

代码提供错误:

NN.fit_generator(
                        train_set, train_labels,
                        steps_per_epoch=(train_samples/ batch_size),
                        epochs=epochs,
                        validation_data=(validation_set, validation_labels),
                        validation_steps=(validation_samples / batch_size))

完整代码: https://pastebin.com/V1YwJW3X

对于此问题的任何帮助，我将不胜感激，因为我不知所措.谢谢！

I would GREATLY appreciate any help with the issue, as I am at a total loss. Thank you!

推荐答案

Keras文档为fit_generator提供了以下定义:

fit_generator(self, generator, steps_per_epoch=None, epochs=1, verbose=1, callbacks=None, validation_data=None, validation_steps=None, class_weight=None, max_queue_size=10, workers=1, use_multiprocessing=False, shuffle=True, initial_epoch=0)

您提供了两个位置参数:

You have provided two positional arguments:

• train_set-这已分配给generator
• train_labels-这已分配给steps_per_epoch

• train_set - this got assigned to generator
• train_labels - this got assigned to steps_per_epoch

但是随后您提供了另一个(现在为关键字参数)steps_per_epoch，因此出现了错误.

But then you provide another (now keyword argument) steps_per_epoch, hence the error.

这篇关于带有Keras错误的多分类NN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！