Goal of this project was to develop and train a Deep learning model capable of detecting and covering license plates of vehicles. This project was implemented with Python using the Keras framework on top of Tensorflow. A number of python libraries like OpenCV, Numpy, Pandas, etc… were used. A lot of work done in order the reduce the overall size of the code and model weights to allow a deployment in Serverless environments like AWS Lambda and Google Cloud Functions. Finally i was able to deploy on Google Cloud Function with an API in front.

In this post, we will outline key learnings from a real-world example of running inference on a sci-kit learn model using the ONNX Runtime API in an AWS Lambda function. This is not a tutorial but rather a guide focusing on useful tips, points to consider, and quirks that may save you some head-scratching! The Open Neural Network Exchange (ONNX) format is a bit like dipping your french fries into a milkshake; it shouldn't work but it just does. ONNX allows us to build a model using all the training frameworks we know and love like PyTorch and TensorFlow and package it up in a format supported by many hardware architectures and operating systems. The ONNX Runtime is a simple API that is cross-platform and provides optimal performance to run inference on an ONNX model exactly where you need them: the cloud, mobile, an IoT device, you name it!

For this project, I wanted to design a model that would do a simple classification of whether a phrase is positive or negative. Since I'm only looking for a binary result, I chose to use Sklearn's logistic regression module. If you were trying to predict more than two labels, you would have to use a different ML model. The data used is a corpus of 5,000 movie reviews -- 2,500 positive and 2,500 negative. The model has an accuracy of 90% and probably performs better with text that is similar to a review because it would more like the training data.

Serverless compute abstracts away provisioning, managing severs and configuring software, simplifying model deployment. Aimed towards becoming a Full Stack Data Scientist. Serverless is the next step in Cloud Computing. This means that servers are simply hidden from the picture. In serverless computing, this separation of server and application is managed by using a platform.

I remember the first time I created a simple machine learning model. It was a model that could predict your salary according to your years of experience. And after making it, I was curious about how I could deploy it into production. If you have been learning machine learning, you might have seen this challenge in online tutorials or books. You can find the source code here if you are interested.

Serverless is the next step in Cloud Computing. This means that servers are simply hidden from the picture. In serverless computing, this separation of server and application is managed by using a platform. The responsibility of the platform or serverless provider is to manage all the needs and configurations for your application. These platforms manage the configuration of your server behind the scenes.