Sovit Rath
In this article, we train the KerasCV YOLOv8 Large model on a traffic light detection dataset.
In this article, we are fine tuning the TrOCR Small Printed model on the SCUT CTW1500 dataset to improve its performance on curved text.
In this article, we explore TrOCR architecture, models, training strategy and run inference using HuggingFace.
In this article, we explore several Re-ID models for tracking along with object detection models from Torchvision to create a small modular codebase.
In this article, we train the YOLO NAS model on a custom dataset, evaluate it and run inference using the trained model.
In this article, we explore how to train the YOLOv8 instance segmentation models on custom data.
This article explores the Segment Anything mode, a foundation model for image segmentation trained on 1.1 billion masks.
In this article, we explore the ControlNet models for image generation which give uses more ControlNet while generating images for a particular pose or style.
In this article, we discuss what is InstructPix2Pix, how it works, how it is trained, and what kind of image editing it can do.
This article lays out all the essential events, talks, and sessions of the much awaited NVIDIA GTC Spring 2023 edition.
In this article, we explore the Stable Diffusion model and how it works under the hood. We explore its training and inference strategy and visit the several variations of Stable
In this article, we explore several AI Art Generation Tools which includes websites, open source projects, and AI generated image search engines.
