kyunghunNam's repositories
opt_seminar
Korea University Korea University, General Graduate School of Artificial Intelligence. Efficient learning and inference lab
detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
tfjs-models
Pretrained models for TensorFlow.js
Pose2Seg
Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.
Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
pyskl
A toolbox for skeleton-based action recognition.
yolact
A simple, fully convolutional model for real-time instance segmentation.
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
vit-pytorch
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
sam
SAM: Sharpness-Aware Minimization (PyTorch)
homura
homura is a library for fast prototyping DL research
SDL-Skeleton
A toolbox for object skeleton detection, can also be used for edge detection, building extraction and road extraction. TIP (2021)
loss-landscape
Code for visualizing the loss landscape of neural nets
namkyunghun.github.com
For my GitBlog
ASAM
Implementation of ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks, ICML 2021.
IIPL_Ptransformer
IIPL_Ptransformer
PixelLibInstanceSegmentation
Real Time instance segmentation using PixelLib and Mask-RCNN
BA780-Airbnb-Project
Team project for BA780 (Introduction to Data Analytics)
loss-landscapes
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
nsmc
Naver sentiment movie corpus