简体繁体 English

Tensorflow 和 Keras 有什么区别？

[英]What is the difference between Tensorflow and Keras?

原文 2019-11-20 19:44:53 8 1 python/ tensorflow/ machine-learning/ keras/ deep-learning

I am currently working with neural networks in keras and I know that it works with tensorflow in the back-end, I have it installed on the GPU, but I don't know if keras uses the GPU or if it is something completely different from tensorflow. I am currently working with neural networks in keras and I know that it works with tensorflow in the back-end, I have it installed on the GPU, but I don't know if keras uses the GPU or if it is something completely different from tensorflow。

1 个解决方案

TensorFlow is a mid-level framework that performs operations on tensors. TensorFlow 是一个对张量执行操作的中级框架。 Keras is a high-level API that simplifies the creation and training of neural networks. Keras 是一个高级 API，它简化了神经网络的创建和训练。 Keras doesn't do any of the tensor ops itself; Keras 本身不执行任何张量操作； it delegates those to its backend, which is a mid-level framework of your choosing: TensorFlow, CNTK, or Theano.它将这些委托给后端，这是您选择的中级框架：TensorFlow、CNTK 或 Theano。 Each of those frameworks can be configured to do the tensor ops in whatever ways they can (as far as I am aware, each of them can use either CPUs or GPUs).这些框架中的每一个都可以配置为以任何方式执行张量操作（据我所知，它们中的每一个都可以使用 CPU 或 GPU）。 Keras, however, doesn't really care how the ops get done.然而，Keras 并不真正关心操作是如何完成的。 It just tells the backend to do them, and they get done.它只是告诉后端去做它们，然后它们就完成了。