Stars
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
Edge-enhanced Feature Distillation Network for Efficient Super-Resolution (CVPRW 2022)
[ECCV 2022] AMixer: Adaptive Weight Mixing for Self-attention Free Vision Transformers
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
On Efficient Transformer-Based Image Pre-training for Low-Level Vision
Collect super-resolution related papers, data, repositories
RepVGG: Making VGG-style ConvNets Great Again
[ECCV 2022] Patch Similarity Aware Data-Free Quantization for Vision Transformers
Slimmable Networks, AutoSlim, and Beyond, ICLR 2019, and ICCV 2019
Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR
Codes for ACMMM 2021 paper "Fully Quantized Image Super-Resolution Networks".
pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…
The state-of-the-art image restoration model without nonlinear activation functions.
FFCV: Fast Forward Computer Vision (and other ML workloads!)
An Open-Source Library for Training Binarized Neural Networks
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"
Convolutional Neural Network with CUDA (MNIST 99.23%)
Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.