Keras official Chinese version

Keras is a high-level neural network API written in Python that can be run TensorFlow, CNTK, or Theano as a backend. "Keras is more of an interface than an independent machine learning framework," said François Chollet, Keras's author, a Google engineer.

Keras allows for simple and rapid prototyping (user-friendly, highly modular, scalable) while supporting convolution neural networks and cyclic neural networks, as well as a combination of both, and can be seamlessly run and switched on both the CPU and GPU. Overall, Keras has the following major advantages:

User friendliness: Keras provides a consistent and concise API that greatly reduces the workload of users under general application, while Keras provides clear and practical bug feedback.

Modularity: A model can be understood as a sequence or data graph of a layer, and fully configurable modules can be combined at least at the cost of freedom. Specifically, network layer, loss function, optimizer, initialization strategy, activation function, regularization method are all independent modules, and you can use them to build your own model.

Scalability: It's super easy to add new modules, just write new classes or functions in the same mode as the existing ones. The convenience of creating new modules makes Keras more suitable for advanced research work.

Collaboration with Python: Keras does not have a separate model profile type (as a contrast, Caffe has), the model is described by Python code, makes it more compact and easier to debug, and offers extended convenience.

As of November 2017, the number of Keras users has exceeded 200,000. It can be said that the fiery Keras has already spread to China. Some of the volunteers translated Keras's English documents (https://keras-cn.readthedocs.io/en/latest/) early to benefit their countrymen.

Recently, François Chollet announced on Twitter, "the Chinese version of Keras is coming." ”

From the Keras Chinese version of the following figure, it can be seen that the Chinese version of the document is not complete. From the processing section, the documentation is still in English, and the full Chinese version is expected to take some time.

--------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- --------------------------------------------------------------------------------------------------------------- ---------------------------------------------------------------------------------------------------------------- ---------------------------------------------------------