Nkiruka Uzuegbunam's repositories
action_recognition
Solving UCF-101 with fastai2
checkered-cnn
A new technique to increase receptive field in convolutional neural networks without losing so much information.
contextualLoss
The Contextual Loss
cs50w_lesson0
Testbed for re/learning Git and Github with variety of sources
DecoupleLearning
Implementation codes of ECCV 2018 paper "Decouple Learning for Parameterized Image Operators"
DeepColoring
Instance Segmentation by Deep Coloring
dino-vit-features
Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".
hyperstyle
Official Implementation for "HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing" https://arxiv.org/abs/2111.15666
image-outpainting
Final project for CS 230, Spring 2018.
insightface
State-of-the-art 2D and 3D Face Analysis Project
linformer-pytorch
My take on a practical implementation of Linformer for Pytorch. https://arxiv.org/pdf/2006.04768.pdf
mmaction2
OpenMMLab's Next Generation Action Understanding Toolbox and Benchmark
progressive_growing_of_gans
Progressive Growing of GANs for Improved Quality, Stability, and Variation
RSICD_optimal
Datasets for remote sensing images (Paper:Exploring Models and Data for Remote Sensing Image Caption Generation)
sifar-pytorch
super image for action recognition
SkyAR_Paddle_GUI
A Paddle and GUI implementation of SkyAR
StressNet-Detecting-stress-from-thermal-videos
StressNet: Detecting Stress in Thermal Videos
superpixel_fcn
[CVPR‘20] SpixelFCN: Superpixel Segmentation with Fully Convolutional Network
torchdiffeq
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
vid2vid
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.