TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frame…

Berkeley's Spatial Array Generator

Exploiting Diffusion Prior for Real-World Image Super-Resolution

ncnn is a high-performance neural network inference framework optimized for the mobile platform

OpenMMLab YOLO series toolbox and benchmark

United Perception

该项目实现了图像超分辨率算法ELAN的TensorRT版本。

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

OpenMMLab Image and Video Editing Toolbox

OpenMMLab Image Classification Toolbox and Benchmark

A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-…

Super-Efficient Super Resolution

Tengine is a lite, high performance, modular inference engine for embedded device

Caffe: a fast open framework for deep learning.

命令行表格

RepVGG TensorRT int8 量化，实测推理不到1ms一帧！

Asymmetric CNN for image super-resolution (IEEE Transactions on Systmes, Man, and Cybernetics: Systems 2021)

PArameterized Max Scale

Learning Continuous Image Representation with Local Implicit Image Function

⚡Super fast and lightweight anchor-free object detection model. 🔥Only 1.8mb and run 97FPS on cellphone🔥

Easily display progress in C++17. Inspired by python's awesome tqdm library.

Repository containing an independent implementation of the paper: "A Fully Progressive Approach to Single-Image Super-Resolution"

Rethinking Data Augmentation for Image Super-resolution (CVPR 2020)

Deep Residual Learning for Image Recognition