如何使用支持生成器的 Model.fit(在 fit_generator 弃用后) [英] How to use Model.fit which supports generators (after fit_generator deprecation)

问题描述

我在 tensorflow 中使用 Model.fit_generator 时收到了这个弃用警告:

I have got this deprecation warning while using Model.fit_generator in tensorflow:

WARNING:tensorflow: Model.fit_generator (from tensorflow.python.keras.engine.training) is deprecated and will be removed in a future version.
Instructions for updating:
Please use Model.fit, which supports generators.

如何使用 Model.fit 而不是 Model.fit_generator?

How can I use Model.fit instead of Model.fit_generator?

推荐答案

Model.fit_generator 从 tensorflow 2.1.0 开始被弃用，目前在 rc1 中.您可以在此处找到 tf-2.1.0-rc1 的文档:https://www.tensorflow.org/versions/r2.1/api_docs/python/tf/keras/Model#fit

Model.fit_generator is deprecated starting from tensorflow 2.1.0 which is currently is in rc1. You can find the documentation for tf-2.1.0-rc1 here: https://www.tensorflow.org/versions/r2.1/api_docs/python/tf/keras/Model#fit

正如您所见，Model.fit 的第一个参数可以接受一个生成器，因此只需将您的生成器传递给它即可.

As you can see the first argument of the Model.fit can take a generator so just pass it your generator.

这篇关于如何使用支持生成器的 Model.fit(在 fit_generator 弃用后)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！