AI

How did ChatGPT put code reviews on steroids for this open source community?

Reviewing PRs (GitHub Pull Requests) is one of the most important, yet time-consuming and thankless, jobs open-source maintainers must do on a regular basis. Accurate and speedy review of PRs is not only essential for the cadence of software development but also critical for the moral of the contributor community. The WasmEdge community (a leading WebAssembly Runtime under CNCF and Linux Foundation) recently added a ChatGPT-based PR review bot in our open source GitHub repo.…

Deploying Tensorflow models in production with less than 50 lines of code

Serverless Tensorflow functions in public clouds For software developers and students, artificial intelligence pays. In 2021, the average annual salary for Tensorflow (a popular AI framework) developers is $148,508. Skills in artificial intelligence are now mandatory in even entry level programming jobs. In fact, it is quite easily to follow an online tutorial and train your own Tensorflow model for tasks such as image recognition and natural language processing. You only need some basic Python knowledge to do the training and then run the model for a demo.…

A WASI-like extension for Tensorflow

AI inference is a computationally intensive task that could benefit greatly from the speed of Rust and WebAssembly. However, the standard WebAssembly sandbox provides very limited access to the native OS and hardware, such as multi-core CPUs, GPU and specialized AI inference chips. It is not ideal for the AI workload. The popular WebAssembly System Interface (WASI) provides a design pattern for sandboxed WebAssembly programs to securely access native host functions.…

AI as A Service on WebAssembly

AI inference is an ideal use case for Function as a Service (FaaS). The inference operation is transactional, often happens on the edge, need to scale up and down quickly, and integrates with other network services for input and output. However, the inference is also ill-suited for today's FaaS infrastructure. Inference is computationally intensive and time sensitive. FaaS today has long cold start time, and poor runtime performance due to the heavy runtime software stack and inefficient programming languages.…

AI as a Service: Face Detection Using MTCNN

The MTCNN is a class of Multi-task Cascaded Convolutional Network models. They are very good at detection faces and facial features. You can train (or retrain) MTCNN models with your own faces dataset so that it can accurately detect faces for your application. Second State FaaS provides a Rust API to run Tensorflow-based MTCNN models at native speeds. In this article, we will use the original MTCNN model trained in the FaceNet dataset as an example.…

Image Classification as A Service in Node.js

In the previous article, we discussed how WebAssembly could tie together native TensorFlow, Node.js JavaScript, and Rust functions to create high performance and safe web services for AI. In this article, we will discuss how to apply this approach to ImageNet's MobileNet image classification model, and more importantly, how to create web applications for your own retrained MobileNet models. NOTE This article demonstrates how to call operating system native programs from the SSVM.…

High performance and safe AI as a Service in Node.js

Today’s dominant programming language for AI is Python. Yet, the programming language for the web is JavaScript. To provide AI capabilities as a service on the web, we need to wrap AI algorithms in JavaScript, particularly Node.js. However, neither Python nor JavaScript by itself is suitable for computationally intensive AI applications. They are high-level, ie, slow, languages with heavy-weight runtimes. Their ease-of-use comes at the cost of low performance. Python got around this by wrapping AI computation in native C/C++ modules.…