Keras 简明教程
Keras - Backend Configuration
本章详细解释了Keras后端实施TensorFlow和Theano。让我们逐一了解每个实施。
This chapter explains Keras backend implementations TensorFlow and Theano in detail. Let us go through each implementation one by one.
TensorFlow
TensorFlow 是 Google 开发的用于数字计算任务的开源机器学习库。Keras 是建立在 TensorFlow 或 Theano 之上的一个高级别 API。我们已经知道如何使用 pip 安装 TensorFlow。
TensorFlow is an open source machine learning library used for numerical computational tasks developed by Google. Keras is a high level API built on top of TensorFlow or Theano. We know already how to install TensorFlow using pip.
如果没有安装，可以使用以下命令安装：
If it is not installed, you can install using the below command −
pip install TensorFlow一旦执行 Keras，我们就能够看到配置文件位于你的主目录中，进入 .keras/keras.json。
Once we execute keras, we could see the configuration file is located at your home directory inside and go to .keras/keras.json.
keras.json
{
"image_data_format": "channels_last",
"epsilon": 1e-07, "floatx": "float32", "backend": "tensorflow"
}在此，
Here,
-
image_data_format represent the data format.
-
epsilon represents numeric constant. It is used to avoid DivideByZero error.
-
float*x represent the default data type *float32. You can also change it to float16 or float64 using set_floatx() method.
-
image_data_format represent the data format.
假设如果没有创建这个文件，那么就移动到相应位置，然后使用以下步骤创建：
Suppose, if the file is not created then move to the location and create using the below steps −
> cd home
> mkdir .keras
> vi keras.json记住，你应该将其文件夹名称指定为 .keras，并在 keras.json 文件中添加以上配置。我们可以执行一些预定义的操作以了解后端函数。
Remember, you should specify .keras as its folder name and add the above configuration inside keras.json file. We can perform some pre-defined operations to know backend functions.
Theano
Theano 是一个开源深度学习库，允许你高效地计算多维数组。我们可以使用以下命令轻松安装：
Theano is an open source deep learning library that allows you to evaluate multi-dimensional arrays effectively. We can easily install using the below command −
pip install theano默认情况下，Keras 使用 TensorFlow 后端。如果你想把后端配置从 TensorFlow 更改为 Theano，只需在 keras.json 文件中将 backend = theano 更改一下即可。如下所述：
By default, keras uses TensorFlow backend. If you want to change backend configuration from TensorFlow to Theano, just change the backend = theano in keras.json file. It is described below −