Sanbu's Projects
A kubernetes plugin which enables dynamically add or remove GPU resources for a running Pod
申请季材料汇总,给学弟学妹们提供一些参考。(PS, SOP, CV, etc.)
hands on model tuning with TVM and profile it on a Mac M1, x86 CPU, and GTX-1080 GPU.
how to optimize some algorithm in cuda.
row-major matmul optimization
有关高性能计算与边缘计算部署相关的资料
Hugging StableDiffusion, Hugging Future.
HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance
基于深度学习高性能中文车牌识别 High Performance Chinese License Plate Recognition Framework.
C++ Helper Class for Deep Learning Inference Frameworks: TensorFlow Lite, TensorRT, OpenCV, OpenVINO, ncnn, MNN, SNPE, Arm NN, NNabla, ONNX Runtime, LibTorch, TensorFlow
中学历史学科作为培养学生综合素质和历史意识的重要学科,对于学生的发展具有深远的影响。为了提升中学生对历史学科的学习效果,开发基于InternLM大模型的中学历史学习助手。
A CPU+GPU Profiling library that provides access to timeline traces and hardware performance counters.
一个存放垃圾的地方
b站上的课程
一个推理库的实现, A DIY deep learning inference framework.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
MIT视频公开课《计算机程序的构造和解释》中文化项目及课程学习资料搜集。
An open source library for face detection in images. The face detection speed can reach 1000FPS.
A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.
LightSeq: A High Performance Library for Sequence Processing and Generation
Collection of image and video datasets for generative AI and multimodal visual AI
记录近期的 1) 图像/视频的超分增强等low level vision任务; 2) 图像生成 等任务相关论文, 主要为18年以后的DL based方法.
自己实现一个tensor add 计算图,并对其结果
OpenMMLab Image Classification Toolbox and Benchmark
OpenMMLab Model Deployment Framework
OpenMMLab Detection Toolbox and Benchmark
OpenMMLab Foundational Library for Training Deep Learning Models
OpenMMLab YOLO series toolbox and benchmark