pianoggg Goto Github PK

armneonoptimization

Arm neon optimization practice

awesome-autodl

A curated list of automated deep learning (including neural architecture search and hyper-parameter optimization) resources.

books

cmake_tutorial

all cmake tutorial demo mirror

cmaketutorial

CMake中文实战教程

cogito

收集知乎用户@佐藤謙一 先生回答86个

dpir

Deep Plug-and-Play Image Restoration (PyTorch)

es-fastloader

Quickly build large-scale ElasticSearch indices by using the fault tolerance and parallelism of Hadoop

fastervit

Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

gbdt

A simple GBDT in Python

helloword

how-to-optimize-gemm

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.

interview-notebook

:books: 技术面试需要掌握的基础知识整理，欢迎编辑~

leetcode

记录LeetCode的解答过程

libpku

贵校课程资料民间整理

machinelearning

Basic Machine Learning and Deep Learning

mit-ml

斯坦福机器学习完整 python 实现

mnn

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

msnhnet

🔥 (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.

mypicture

Picture of my blog or project

ncnn

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

optimizing-sgemm-on-nvidia-turing-gpus

Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

quantization-keras-and-tensorflow

Implement quantization-aware training with Keras and convert to .pb.

repo_git_demo

robustvideomatting

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

scikit-learn

scikit-learn: machine learning in Python

sourceinsighttheme

Source Insight 4 Theme, Sublime style

styletransfer

Implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" in PyTorch

tengine

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