joannelin168 Goto Github PK

2021-armessaging

SkyWrite is an Android app that will allow a sender to select an appropriate message (eg Happy Birthday, Merry Christmas etc) to a postcode. The message will appear in augmented reality 100ft above the ground. Those with the app/service will be notified that a message exists in a nearby postcode.

ads-european-productivity

brain-tumours-mri-classification

cg2022

cnn-fruit-detector

A convolutional neural network to detect apples, oranges and bananas

cocoapi

Clone of COCO API - Dataset @ http://cocodataset.org/ - with changes to support Windows build and python3

computergraphicsrenderer

coms20011_2021

Data-driven Computer Science UoB

imagenet-adversarial-training

ImageNet classifier with state-of-the-art adversarial robustness

joannelin168.github.io

Joanne Lin's Research Portfolio

ltr-weight-balancing

CVPR 2022 - official implementation for "Long-Tailed Recognition via Weight Balancing" https://arxiv.org/abs/2203.14197

marioml

Developing a program in python that can predict if the image inputted is Mario or not

ml_lab_sheets

optijj-gamejam-2020

os161

ops-class.org OS/161 sources.

pongml

A deep-learning program that teaches itself how to play Pong. Will create images of the graphs showing the trends of the program when the program finishes (i.e. when the user chooses to or when the program has reached its maximum number of generations)

rt-detr

[CVPR 2024] Official RT-DETR (RTDETR paddle pytorch), Real-Time DEtection TRansformer, DETRs Beat YOLOs on Real-time Object Detection. 🔥 🔥 🔥

santas-workshop

A simulation to track how long it will take for Santa and the elves to prepare presents for children

star-pytorch

Implementation for paper "STAR: A Structure-aware Lightweight Transformer for Real-time Image Enhancement"

vim

Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

visionmamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images

vivim

Vivim: a Video Vision Mamba for Medical Video Lesion Segmentation