EverestRs

FastestDet

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

Huawei-Atlas200DK-Car

Embedded System Design | Tongji University, 2020

HTRPN

Init commit for HTRPN

edgevit

[ECCV 2022] EdgeViT: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

Atlas_ACL_E2E_Demo

FP8-quantization

st-gcn

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

QR_decode_for_Arduino

QR decode for Arduino Library including Spresense examples

AnnotatedCode

知名开源代码库的注释版：C++、Golang等

annotated-transformer

An annotated implementation of the Transformer paper.

random_wave_attention_encoder

(wave random encoder ,WRE);(svd wave attention,SWA)

xv6-riscv

Xv6 for RISC-V

xv6-public

xv6 OS

RepVGG

RepVGG: Making VGG-style ConvNets Great Again

RenderHelp

:zap: 可编程渲染管线实现，帮助初学者学习渲染

DeepLearning-500-questions

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

ThermalGesture_ESP32

在ESP32上实现基于红外热成像阵列传感器的手势识别

MIT-6.S965-TinyML-and-Efficient-Deep-Learning-Computing

iccad-tinyml-open

[ICCAD'22 TinyML Contest] Efficient Heart Stroke Detection on Low-cost Microcontrollers

6.S965

CUDA_Freshman

efficient-feature-matching

Course project for 6.S965: TinyML & Efficient Deep Learning Computing at MIT 2022.

DynamicOFA

[CVPRW 2021] Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms

HAR-ON-STM32F401C

使用卷积神经网络在STM32F401C-DISCO上实现人体活动识别

How_to_optimize_in_GPU

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

GeoProj

Blind Geometric Distortion Correction on Images Through Deep Learning

Portraits_Correction

Distortion-Free-Wide-Angle-Portraits

The C++ realization of the paper Distortion-Free Wide-Angle Portraits on Camera Phones by Shih et al.

Thermal-YOLO-And-Model-Optimization-Using-TensorFlowLite

This repo contains all the codes. trained models, optimized version of models using TensorflowLite tool and validatation results

xv6-riscv-book

Text describing xv6 on RISC-V