This article details how to build high-performance scalable models for a variety of systems and network topologies.

On September 20, 2018, Laurence Moroney, Google Developer Technology Outreach Engineer, and Yizhen Fu, Software engineer at Google Brain, present at "Introduction to TensorFlow: Introduction to the Use of Machine learning techniques. This article will provide a review of the presentation. From a programmer's point of view...

The so-called image style transfer refers to the technology of fusing the content of A content picture A with the style of A style picture B, so as to generate A picture C with the style of A and the content of B. At present, this technology has been widely used. Here is an app called "Great Painter", which can automatically transform users' photos into images with the style of an artist. Actually, I just started writing this article...

We ranked 23 open source deep learning libraries for data science. The ranking is based on three equally weighted metrics: activity on Github, activity on Stack Overflow and Google search results.

So far, we have implemented a Simple wechat applet deployed on the server side using the open source Simple TensorFlow Serving. However, there is a major problem with this implementation: the image data that the applets communicate with the server is a Json-like representation of the binary array (299, 299, 3). The biggest disadvantage of json-like binary data...

This is the fifth and final article in a series of articles summarizing the development process of wechat mini program Zhigujun when it meets TensorFlow. If you want to know more about this project, you can refer to the first four articles in this series: Today, the wechat public platform sent a message that my wechat mini program Zhigujun was approved. At this point, the development of this project temporarily come to an end. To do this...

In the previous article "When wechat Applets meet TensorFlow: Server-side Implementation", we discussed the server-side implementation of wechat applets. Today, I found a problem when DEBUGGING wechat applet, that is: wechat applet requires HTTP requests to use the more secure HTTPS protocol. For this I studied Simple TensorFlow Serv...

For example, when you speak a sentence, the machine can recognize the text, and understand the meaning of your words, analysis and dialogue. At its most basic, machine learning uses algorithms to parse data, learn from it, and then make decisions and predictions about events. It takes a lot of data to "train", and algorithms to learn how to do things from that data. For example, when browsing online shopping malls, there are often letters recommending products...

First of all, let's make fun of the fact that there is no Linux version of wechat mini program development tool. In order to develop wechat mini program, I had to bring out my entertainment machine iMac. Looking at the huge screen and looking at the words that look like ants, I really want to ask those of you who use iMac as a developer, don't they get shoulder irritation and sore eyes? Without further discussion, in the previous two articles "When wechat applets meet TensorFlow...

Keyword Spotting is often the user's first impression of the voice interaction experience. It should be accurate and quick. Therefore, hot word detection algorithm should ensure high wake up rate and low false wake up rate at the same time, and can accurately distinguish hot word and non-hot word audio signals. Mainstream hot word detection methods usually use deep neural networks to extract high-level abstractions from original audio features...