Kunchang Li's repositories
Nightcrawler
Top-2 Solution for CVPR UG2+ Track2
CS231n-Notes
Notes and resources for CS231n
CrossFormer
The official code for the paper: https://arxiv.org/pdf/2108.00154.pdf
EditAnything
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc.
Kinetics-TPS-evaluation
fork from xiadingZ/Kinetics-TPS-evaluation
Awesome-Anything
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
deit
Official DeiT repository
grounded-segment-any-parts
Grounded Segment Anything: From Objects to Parts
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion - Detect , Segment and Generate Anything with Text Inputs
mae
PyTorch implementation of MAE https//arxiv.org/abs/2111.06377
MAE-pytorch
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
sd-webui-segment-anything
Segment Anything for Stable Diffusion Webui
SKNet-PyTorch
Nearly Perfect & Easily Understandable PyTorch Implementation of SKNet
Swin-Transformer
This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
VideoMAE
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
visual-chatgpt
Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models