TensorRT is a high-performance deep-learning inference engine developed by NVIDIA. It is designed to optimize and accelerate the inference of deep neural networks on NVIDIA GPUs. In this blog, I will guide you on how to install TensorRT on your ubuntu based system. Step 1: Check Prerequisites Before installing TensorRT…

What is an SSL Wildcard Certificate? An SSL Wildcard certificate is a single certificate with a wildcard character (*) in the domain name field. This allows the certificate to secure multiple sub-domain names (hosts) of the same base domain. For example, a wildcard certificate for *.xyz.com, could be used for…

FastAPI is a modern, fast (high-performance), web framework for building APIs in python which is fast to code, asynchronous, and ready for production. Generally, FastAPI’s are deployed using uvicorn which is a lightning-fast ASGI server implementation. Another way of deploying is using NGINX Unit which is a lightweight, open-source app…

Building an iterable object from scratch is easy in python, in this tutorial you will be able to learn how iterator works. …

Serving an image classification model in production and inferencing with gRPC or rest API call — Tensorflow provides a variety of ways to deploy the model. I have explored most of the ways of serving a model in production. I was looking out for a simple, secure, and robust solution that should be easy to access on both edge devices as well as servers written on…

Yet another way of inferencing an image classification model for reducing inference time by directly deploying in a static website or nodejs web application. Deploying a machine learning model can be fun. You have to make sure you have setup with hardware and software optimized pipeline and boom your model…

Training a convolutional neural network to classify images from the dataset and use TensorBoard to explore how its confusion matrix evolves. — Tensorboard is the best tool for visualizing many metrics while training and validating a neural network. In most of the case, we need to look for more details like how a model is performing on validation data. Sometimes training and validation loss and accuracy are not enough, we need to…

Observing the neural network training process is equally important as it helps observe loss and accuracy per epoch and much more. — While training your model in python, the tensorboard library makes it possible to do visualization. Similarly, if you are training your model on a browser with tensorflowjs, you will require something for watching the training process. It is possible using the tensorflowjs visualizer. Using this, we can visualize the training…

The latest update from Ubuntu 20.04 (focal fossa) has changed the look and feel of the operating system. With new OS comes new challenges especially for users like me who are after trying out something new every time. …