Name: Lahiru Rumesh Rathnayake
Type: User
Bio: AI researcher specializing in machine learning and computer vision, Exploring the nexus of data science innovations.
Twitter: LahiRumesh
Location: Kandy, Sri Lanka
Lahiru Rumesh Rathnayake's Projects
data pipeline use for cnn
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
End-to-End Object Detection with Transformers
k-means clustering with the Intersection over Union (IoU) metric as described in the YOLO9000 paper
An ecosystem of Rust libraries for working with large language models
Data Pre-Processing for Machine Learning
A collection of pre-trained, state-of-the-art models in the ONNX format
PyTorch ,ONNX and TensorRT implementation of YOLOv4
SOTA Semantic Segmentation Models in PyTorch
Simple CNN is a library that can be used to train and infer CNN models by use of PyTorch and ONNX.
Semi-Supervised | Pseudo Labeling pipeline with one-stage object detection models
YOLOv4, YOLOv4-tiny, YOLOv3, YOLOv3-tiny Implemented in Tensorflow 2.0, Android. Convert YOLO v4 .weights tensorflow, tensorrt and tflite
Tensorflow implementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)
How to create custom COCO data set for object detection
label file converter: xml to yolo
A simple, fully convolutional model for real-time instance segmentation.
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
YoloV3 Implemented in Tensorflow 2.0
convert trained yolov3 weights (.h5) model to TensorFlow severing