PyTorch

DeepLabv3 & DeepLabv3+ The Ultimate PyTorch Guide

DeepLab models, first debuted in ICLR ‘14, are a series of deep learning architectures designed to tackle the problem of semantic segmentation. After making iterative refinements through the years, the

Deep Learning, Image Segmentation, PyTorch, Segmentation

The Future of Image Recognition is Here: PyTorch Vision Transformers

In this article, we show how to implement Vision Transformer using the PyTorch deep learning library.

Deep Learning, Neural Network, PyTorch, Transformer Neural Networks, Vision Transformer

Meet YOLO-NAS: New YOLO Object Detection Model Beats YOLOv6 & YOLOv8

YOLO-NAS is the new real-time SOTA object detection model. YOLO-NAS models outperform YOLOv7, YOLOv8 & YOLOv6 3.0 models in terms of mAP and inference latency.

Computer Vision, Object Detection, PyTorch, YOLO

Train YOLOv8 Instance Segmentation on Custom Data

In this article, we explore how to train the YOLOv8 instance segmentation models on custom data.

Object Detection, PyTorch, Segmentation, YOLO

Enhancing Medical Multi-Label Image Classification Using PyTorch & Lightning

Medical diagnostics rely on quick, precise image classification. Using PyTorch & Lightning, we fine-tune EfficientNetv2 for medical multi-label classification.

CNN, Deep Learning, Image Classification, Medical Imaging, PyTorch, PyTorch-Lightning

Weighted Boxes Fusion in Object Detection: A Comparison with Non-Maximum Suppression

Weighted box fusion: The post-processing step is a trivial yet important component in object detection. In this article, we will demonstrate the significance of Weighted Boxes Fusion (WBF) as opposed

Deep Learning, Object Detection, PyTorch, YOLO