Resources_I_Perferred.md

Record the userful Resources of ML I saw.

I put a (1-5) recommend level after each resource I deep used or readed.

Projects @ Github

• humphd/have-fun-with-machine-learning (5)

This is a hands-on guide to machine learning for programmers with no background in AI. It guide you using NVIDIA/DIGITS to train the CNN caffe mode examples(AlexNet & GoogleNet) step step. I open the door of ML/DL through this project.

Here

• Microsoft/MMdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

Here

• purelyvivid/MMdnn-util Introduces the utilization of MMdnn(a model converter) and provide a simple GUI for inference task of image classification. Here

• Awesome Machine Learning A curated list of awesome machine learning frameworks, libraries and software (by language). Here

• ZuzooVn/machine-learning-for-software-engineers

Top-down learning path: Machine Learning for Software Engineers

Here

• kailashahirwar/cheatsheets-ai

Essential Cheat Sheets for deep learning and machine learning researchers.

Here

Origin URL

• Shivanandroy/Study-Materials

This repository contains quick reference guides (Books in pdf) to Statistics and Machine Learning algorithms.

Here

• fchollet/deep-learning-with-python-notebooks (5)

This repository contains Jupyter notebooks implementing the code samples found in the book Deep Learning with Python (Manning Publications)

This realy a good book give you both basic concepts and hands-on lab to learn DL with Python/Keras/Tensoflow.

Here

• techfort/pycv (4)

This is the repository and reference website for Learning OpenCV 3 with Python, a book authored by Joe Minichino and Joe Howse, and published by Packt Publishing.

Here

• PacktPublishing/Hands-On-Deep-Learning-with-TensorFlow

This is the code repository for Hands-On Deep Learning with TensorFlow, published by Packt. It contains all the supporting project files necessary to work through the book from start to finish.

Here

• Udacity Computer Vision Nanodegree Program, Exercises Here

• mlcourse.ai – Open Machine Learning Course Here

• exacity/deeplearningbook-chinese 《深度学习》github译本 https://exacity.github.io/deeplearningbook-chinese/ Here

• mml-book/mml-book.github.io Mathematics for Machine Learning(https://mml-book.github.io/) Here

Paper with Code

OPEN REID Deep Learning and stuff papers

• Top Deep Learning Projects A list of popular github projects related to deep learning (ranked by stars). Here

AUTO ML

• OPTUNA Optuna: A hyperparameter optimization framework
• fastai https://github.com/fastai/fastai

PyTorch

pytorch-handbook

Tensorflow

• 简单粗暴 TensorFlow 2 | A Concise Handbook of TensorFlow 2 GitHub ( https://github.com/snowkylin/tensorflow-handbook)

• Google Tensorflow Crash Course

URL

GPU

• GPU加速的编程思想，图解，和经典案例，NVIDIA Python Numba CUDA大法好

Python

• Python3-tutorial in Chinese

RIP Tutorial

• riptutorial Summary many tutorial about different programming language like C/C++/Python/SQL, etc

OpenCV

• Original: https://opencv.org/
• OpenCV Tutorials
• A lite private website about OpenCV
• pyimagesearch , a blog dedicated to computer vision, OpenCV, and deep learning

Data Science

• Towards Data Science, Sharing concepts, ideas, and codes

Machine Learning

• Machine Learning Is Fun

• 李宏毅机器学习(2017)

• a_journey_into_math_of_ml

• 汉语自然语言处理视频教程-开源学习资料

• Start Training on Machine Learning with AWS (30+ digital ML courses totaling 45+ hours, plus hands-on labs and documentation, originally developed for Amazon's internal use. )

• r2d3.us (Give a very cool visual introduction to ML, now just has two parts, Part1 A Decision Tree / Part2 Bias and Variance)

• Open Machine Learning Course mlcourse.ai (mlcourse.ai is an open Machine Learning course by OpenDataScience)

• YOLO object detection with OpenCV

• Collective Knowledge (CK)

• MLperf

• TFLearn

• 神力工业AI工具链

• https://www.murtazahassan.com/

HLS4ML

https://hls-fpga-machine-learning.github.io/hls4ml/

Numpy

• Numpy CN
• teadocs/numpy-cn

Models

Yolo/Darknet

• Darknet Git Repo

• PyTorch-YOLOv3

• Explore Yolo

  • YOLO object detection with OpenCV

  • 5分钟学会AI - How YOLO only look once

  • 5分钟学会AI - How to use YOLO with python

  • 目标检测 - 你真的读懂yolo了吗？（分享自知乎网）

  • 一文看懂YOLO v3

  • 深入理解目标检测与YOLO（从v1到v3）

  • YOLOv3 anchor 机制及损失函数计算详解

  • yolov3 Keras实现解

  • yolov3-tiny

  • EYD与机器学习-yolo系列

    • <机器爱学习>YOLO v1深入理解
    • <机器爱学习>YOLOv2 / YOLO9000 深入理解
    • <机器爱学习>YOLO v3深入理解

  • 腾讯优图：开源YOLO系列代码（含YOLOv3以及各种backbone)

  • YOLOv3通道+层剪枝，参数压缩98%，砍掉48个层，提速2倍！ Git URL

Tools

• Netron Viewer for neural network models Netron supports ONNX (.onnx, .pb, .pbtxt), Keras (.h5, .keras), CoreML (.mlmodel), Caffe2 (predict_net.pb, predict_net.pbtxt), MXNet (.model, -symbol.json) and TensorFlow Lite (.tflite). Netron has experimental support for Caffe (.caffemodel, .prototxt), PyTorch (.pth), Torch (.t7), CNTK (.model, .cntk), PaddlePaddle (model), Darknet (.cfg), scikit-learn (.pkl), TensorFlow.js (model.json, .pb) and TensorFlow (.pb, .meta, .pbtxt).

• Netscope A web-based tool for visualizing neural network architectures (or technically, any directed acyclic graph). It currently supports Caffe's prototxt format.