deep learning
In this article, we cover the basics of training neural networks for beginners for an image classification problem.
In this article, we explore the YOLOv5 instance segmentation architecture and run inference on several videos and images.
Build an AI fitness trainer application that analyzes squats using MediaPipe’s Pose solution and prompts appropriate feedback.
This article explains several performance comparison between different YOLO object detection models. These include YOLOv5, YOLOv6, and YOLOv7.
FCOS: Fully Convolutional One-stage Object Detection is an anchor-free (anchorless) object detector. Inference on image and video with PyTorch.
YOLOX object detector is a recent addition in the YOLO family. Read the article for detailed YOLOX paper explanation and learn how to train YOLOX on a custom dataset.
Let's understand what face detection is, how it works, what its challenges are, and in what areas face detection is used. You will also see the journey of face detection
Moving away from traditional document scanners, learn how to create a Deep Learning-based Document Segmentation model using DeepLabv3 architecture in PyTorch.
This article explains the training pipeline for fine tuning of the YOLOv7 object detection model on a custom pothole detection dataset
In this blog post, we will be training YOLOv4 models on a custom pothole detection dataset using the Darknet framework and carry out inference using the trained models.
Do you want to understand modern GPU features like tensor cores, structured sparsity and transformer engines? If yes, this post is for you. We analyze 5 generations of NVIDIA GPUs
Introduction CUDA programming model2.1 What is CUDA?2.2 Introduction to some important CUDA concepts Implementing a dense layer in CUDA Summary 1. Introduction A few months ago, we covered the launch
