Pinned Repositories
poker-engine-2024
CheXFusion
[ ICCV CVAMD 2023] Official implementation of "CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification" 🏆 1st place solution 🏆 for the ICCV CVAMD 2023 Shared Task: CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays.
CmuMaps
CmuMaps is an indoor navigation system I made in 24hrs during HackCMU
ConvNext-tensorflow
Unofficial Tensorflow Implementation of ConvNeXt from "A ConvNet for the 2020s"
CXR-LT-public-solution
DLB-Pytorch
A minimalist unofficial implementation of "Self-Distillation from the Last Mini-Batch for Consistency Regularization"
DOLG-pytorch
Unofficial PyTorch Implementation of "DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features"
dongkyuk.github.io
Kaggle_Indoor_Loc
PatchConvNet-pytorch
Unofficial PyTorch Implementation of "Augmenting Convolutional networks with attention-based aggregation"
dongkyunk's Repositories
dongkyunk/DOLG-pytorch
Unofficial PyTorch Implementation of "DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features"
dongkyunk/CheXFusion
[ ICCV CVAMD 2023] Official implementation of "CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray Classification" 🏆 1st place solution 🏆 for the ICCV CVAMD 2023 Shared Task: CXR-LT: Multi-Label Long-Tailed Classification on Chest X-Rays.
dongkyunk/PatchConvNet-pytorch
Unofficial PyTorch Implementation of "Augmenting Convolutional networks with attention-based aggregation"
dongkyunk/ConvNext-tensorflow
Unofficial Tensorflow Implementation of ConvNeXt from "A ConvNet for the 2020s"
dongkyunk/DLB-Pytorch
A minimalist unofficial implementation of "Self-Distillation from the Last Mini-Batch for Consistency Regularization"
dongkyunk/Kaggle_Indoor_Loc
dongkyunk/CXR-LT-public-solution
dongkyunk/dongkyuk.github.io
dongkyunk/Kaggle-Foursquare
Simple Silver Medal solution for Kaggle Foursquare Location Matching
dongkyunk/Pytorch-Blocks
All sorts of predefined blocks for pytorch
dongkyunk/ActiveShiftLayer
Pytorch implementation of "Constructing Fast Networkthrough Deconstruction of Convolution"
dongkyunk/climate-hack-ai
dongkyunk/Kaggle_RPS
Agent code for Kaggle Rock Paper Scissors
dongkyunk/LeNet-Pytorch
Pytorch implementation of LeNet. Includes parse options to change optimizer, epoch size, lr rate, momentum and etc. "Ten Papers && Ten Implementations"
dongkyunk/audiocraft-token-merging
Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.
dongkyunk/cross_modal_adaptation
Cross-modal few-shot adaptation with CLIP
dongkyunk/Dacon-multi-mnist
Dacon Computer Vision Competition (🥇 4th place) https://dacon.io/competitions/official/235697/overview/
dongkyunk/dongkyuk
dongkyunk/DSC-Workshop-Streamlit
dongkyunk/generative-interior-design
dongkyunk/HearMe
HearMe is a cross platform mobile application providing a novel way to stay aware of people calling you. It is the winner of the Microsoft Azure Champ Prize 🏆 for TartanHacks 2021.
dongkyunk/Kaggle-Ranzcr-Clip
dongkyunk/Kaggle_NCAA
Prediction Model for 2021 NCAA basketball tournament
dongkyunk/Kaggle_Vent_Pressure
dongkyunk/LOL-Win-Prediction
League of Legends win prediction using only player summoner names, selected roles and champions.
dongkyunk/Poker_AI_Visualizer
dongkyunk/Swin-Transformer-Tensorflow
Unofficial implementation of "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" (https://arxiv.org/abs/2103.14030)
dongkyunk/TeacherMatch_APP_FLASK
RESTful API for The Mentor App Backend
dongkyunk/VectorizedMultiAgentSimulator
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set of challenging multi-robot scenarios. Additional scenarios can be implemented through a simple and modular interface.
dongkyunk/Video-VQVAE
VQVAE for video prediction