• TensorFlow ,theano and Keras are deep learning frameworks. TensorFlow and theano are more flexible and difficult to learn. They are actually a differentiator. Keras is actually the interface between TensorFlow and Keras (Keras as the front end, TensorFlow or theano as the back end), it is also very flexible and easy to learn. You can think of keras as an API after tensorflow encapsulation.

I want to tell my feelings about the two frameworks.

Obviously, I contacted with tensorflow earlier. We all know that tensorflow is an open-source framework which was put forward by Google in 2015. Tensorflow conputation framework can support nearly all kinds of algorithms used in deep learning. It has excellent applications on different fields in deep learning including computer vision, speech recogonition, natural language processing, human-machine game and so on.

Keras prioritizes developer’s experience, which means Keras is an API designed for humans, not machines. Keras follows best practices for reducing cognitive difficulties: It provides a consistent and simple API that minimizes the number of user actions required for common use cases and provides clear and actionable feedback in the event of user error. This ease of use does not come at the expense of flexibility: because Keras is integrated with the underlying deep learning language (especially TensorFlow), it allows you to implement anything you can write in the base language.

Keras is used more easily and friendly than tensorflow. The use of tensorflow needs us to learn the neural network in details and know the meaning of each function and parameter. If you want to do some research on deep learning and the parameters need to be assigned and set by yourself according to different requirements, I think tensorflow is a better choice because it is a detailed bottom frame which can train models accurately. However, when it comes to the data processing and analysis on data in induatrial area, I think keras is better for its convenience and usability.

In the following several blogs, I will compare the two frames in details and there are also some codes to help us learn better. Please look forward to it…