#learnopencv

[learnopencv1]

Understanding Attention Mechanism in Transformer Neural Networks

In this article, we cover the attention mechanism in neural networks in detail and also implement it using PyTorch

[learnopencv1]

Deploying a Deep Learning Model using Hugging Face Spaces and Gradio

This article shows the steps for deploying a deep learning model on HuggingFace Spaces using Gradio.

[learnopencv1]

Train YOLOv8 on Custom Dataset – A Complete Tutorial

In this article, we train YOLOv8 on a custom pothole detection dataset using the Ultralytics YOLO package.

[learnopencv1]

YOLOv6 Custom Dataset Training – Underwater Trash Detection

In this article we train the YOLOv6 Nano, Small, and Large models on a custom Underwater Trash Detection dataset and compare the results wit

[learnopencv1]

Fine Tuning YOLOv7 on Custom Dataset

This article explains the training pipeline for fine tuning of the YOLOv7 object detection model on a custom pothole detection dataset

Since its inception, the YOLO family of object detection models has come a long way. YOLOv7 is the most recent addition to this famous anchor-based single-shot family of object detectors. It comes with a bunch of improvements which include state-of-the-art accuracy and speed.  In this article, we will be fine tuning the YOLOv7 object detection model on a real-world pothole detection dataset.

[learnopencv1]

Object Tracking and Reidentification with FairMOT

Explaining and understanding the inner workings of FairMOT Tracker. Checkout the intermediate outputs, and compare the results with DeepSort

Arguably, the most crucial task of Deep Learning-based Multiple Object Tracking (MOT) is not to identify an object but to re-identify it after occlusion. There are a plethora of trackers available to use, but not all of them have a good re-identification pipeline. In this blog post, we will focus on one such tracker, FairMOT, that revolutionized the joint optimization of detection and re-identification tasks in tracking.