zh583007354
Follow
Stars
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)
This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
High-Resolution Image Synthesis with Latent Diffusion Models
A curated list of neural network pruning resources.
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
A Unified Conditional Framework for Diffusion-based Image Restoration
[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Pytorch implementation of our paper accepted by ICLR 2023 -- "Real-time Image Demoireing on Mobile Devices".
Pytorch implementation of our paper accepted by ICML 2023 -- "Bi-directional Masks for Efficient N:M Sparse Training"
source code for aaai19 "A Generalized Language Model in Tensor Space"
Count the MACs / FLOPs of your PyTorch model.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
[NeurIPS 2021 Spotlight] & [IJCV 2024] SOFT: Softmax-free Transformer with Linear Complexity
Official Repsoitory for "Activate or Not: Learning Customized Activation." [CVPR 2021]
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
RepVGG: Making VGG-style ConvNets Great Again
PyTorch implementation of [1412.6553] and [1511.06530] tensor decomposition methods for convolutional layers.
Code for the NuerIPS'19 paper "Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks"
[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks