You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
在自然语言处理领域中，预训练语言模型（Pre-trained Language Models）已成为非常重要的基础技术。为了进一步促进中文信息处理的研究发展，我们发布了基于全词遮罩（Whole Word Masking）技术的中文预训练模型BERT-wwm，以及与此技术密切相关的模型：BERT-wwm-ext，RoBERTa-wwm-ext，RoBERTa-wwm-ext-large, RBT3, RBTL3。
We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher.
Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.
This repository represents Ultralytics open-source research into future object detection methods, and incorporates our lessons learned and best practices evolved over training thousands of models on custom client datasets with our previous YOLO repository https://github.com/ultralytics/yolov3. All code and models are under active development, and are subject to modification or deletion without notice. Use at your own risk.
** GPU Speed measures end-to-end time per image averaged over 5000 COCO val2017 images using a V100 GPU with batch size 32, and includes image preprocessing, PyTorch FP16 inference, postprocessing and NMS. EfficientDet data from [google/automl](https://github.co...
Object tracking implemented with YOLOv4, DeepSort, and TensorFlow. YOLOv4 is a state of the art algorithm that uses deep convolutional neural networks to perform object detections. We can take the output of YOLOv4 feed these object detections into Deep SORT (Simple Online and Realtime Tracking with a Deep Association Metric) in order to create a highly accurate object tracker.
Demo of Object Tracker on Persons
Demo of Object Tracker on Cars
Getting Started
To get started, install the proper dependencies either via Anaconda or Pip. I recommend Anaconda route for people using a GPU as it configures CUDA toolkit version for you.
This repository provides tutorial code for deep learning researchers to learn PyTorch. In the tutorial, most of the models were implemented with less than 30 lines of code. Before starting this tutorial, it is recommended to finish Official Pytorch Tutorial.
👉Natural Intelligence is still a pretty good idea.
😎TOPICS: scikit-learn,machine-learning,benchmark
⭐️STARS：155, 今日上升数↑:65
👉README：
Human Learning
Machine Learning models should play by the rules, literally.
Project Goal
Back in the old days, it was common to write rule-based systems. Systems that do;
Nowadays, it's much more fashionable to use machine learning instead. Something like;
We started wondering if we might have lost something in this transition. Sure,
machine learning covers a lot of ground but it is also capable of making bad
decision. We've also reached a stage of hype that folks forget that many
classification problems can be handled by natural intelligence too.
This package contains scikit-learn compatible tools that should make it easier
to construct and benchmark rule based systems that are designed by humans. You
can also use it in combination with ML models.
This project builds a self-driving RC car using Raspberry Pi, Arduino and open source software. Raspberry Pi collects inputs from a camera module and an ultrasonic sensor, and sends data to a computer wirelessly. The computer processes input images and sensor data for object detection (stop sign and traffic light) and collision avoidance respectively. A neural network model runs on computer and makes predictions for steering based on input images. Predictions are then sent to the Arduino for RC car control.
Abstract: *Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We a...
👉Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
😎TOPICS: ``
⭐️STARS：15404, 今日上升数↑:112
👉README：
Overview
This repository provides code, exercises and solutions for popular Reinforcement Learning algorithms. These are meant to serve as a learning tool to complement the theoretical materials from
Each folder in corresponds to one or more chapters of the above textbook and/or course. In addition to exercises and solution, each folder also contains a list of learning goals, a brief concept summary, and links to the relevant readings.
All code is written in Python 3 and uses RL environments from OpenAI Gym. Advanced techniques use Tensorflow for neural network implementations.
Want to build your own Alexa? All you will need is an ESP32 and Microphone board.
Demo video and code walkthrough is available here on YouTube
I'm using a microphone breakout board that I've built myself based around the ICS-43434 - but any microphone board will work. The code has been written so that you can either use an I2S microphone or an analogue microphone using the built-in ADC.
I would recommend using an I2S microphone if you have one as they have a lot better noise characteristics.
We open source all the popular deep learning frameworks' model and inference code to do face mask detection.
PyTorch
TensorFlow（include tflite and pb model）
Keras
MXNet
Caffe
** Detect faces and determine whether they are wearing mask. **
** First of all, we hope the people in the world defeat COVID-2019 as soon as possible. Stay strong, all the countries in the world.**
We make face mask detection models with five mainstream deep learning frameworks （PyTorch、TensorFlow、Keras、MXNet和caffe） open sourced, and the corresponding inference codes.
We published 7959 images to train the models. The dataset is composed of WIDER Face and MAFA, we verified some wrong annotations. You can download here from Google drive, if you can not vis...
These notebooks cover an introduction to deep learning, fastai, and PyTorch. fastai is a layered API for deep learning; for more information, see the fastai paper. Everything in this repo is copyright Jeremy Howard and Sylvain Gugger, 2020 onwards.
These notebooks are used for a MOOC and form the basis of this book, which is currently available for purchase. It does not have the same GPL restrictions that are on this draft.
The code in the notebooks and python .py files is covered by the GPL v3 license; see the LICENSE file for details.
The remainder (including all markdown cells in the notebooks and other prose) is not licensed for any redistribution or change of format or medium, other than making copies of the notebooks or forking this repo...
👉A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
by cloning this repository and running Jupyter locally. This option lets you play around with the code. In this case, follow the installation instructions below,
or by running the notebooks in Deepnote. This allows you to play around with the code online in your browser...
This book aims to show how ML can add value to algorithmic trading strategies in a practical yet comprehensive way. It covers a broad range of ML techniques from linear regression to deep reinforcement learning and demonstrates how to build, backtest, and evaluate a trading strategy driven by model predictions.
In four parts with 23 chapters plus an appendix, it covers on over 800 pages:
important aspects of data sourcing, financial feature engineering, and portfolio management,
the design and evaluation of long-short strategies based on supervised and unsupervised ML algorithms,
how to extract tradeable signals from financial text data like SEC filings, earnings call transcript...
The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision.
Installation
We recommend Anaconda as Python package management system. Please refer to pytorch.org <https://pytorch.org/>_
for the detail of PyTorch (torch) installation. The following is the corresponding torchvision versions and
supported Python versions.
Update July: Added support for action recognition and tracking
in the new release v1.2.
Computer Vision
In recent years, we've see an extra-ordinary growth in Computer Vision, with applications in face recognition, image understanding, search, drones, mapping, semi-autonomous and autonomous vehicles. A key part to many of these applications are visual recognition tasks such as image classification, object detection and image similarity.
This repository provides examples and best practice guidelines for building computer vision systems. The goal of this repository is to build a comprehensive set of tools and examples that leverage recent advances in Computer Vision algorithms, neural architectures, and operationalizing such systems. Rather than creating implementions from scratch, we draw from existing state-of-the-art libraries and build additional utility around loading image data, optimizing and evaluating mo...
👉Automatic headphone equalization from frequency responses
😎TOPICS: ``
⭐️STARS：2250, 今日上升数↑:13
👉README：
AutoEQ
TL;DR If you are here just looking to make your headphones sound better, find your headphone model in results folder's recommended headphones list
and follow instructions in Usage section.
About This Project
AutoEQ is a project for equalizing headphone frequency responses automatically and it achieves this by parsing
frequency response measurements and producing equalization settings which correct the headphone to a neutral sound.
This project currently has over 2500 headphones covered in the results folder.
See Usage for instructions how to use the results with
different equalizer softwares and Results section for details about parameters and how the results were
obtained.
AutoEQ is not just a collection of automatically produced headphone equalization settings but also a tool for equalizing
headphones for yourself. autoeq.py provides methods for reading data, equalizing it to a given target
response and saving the results for u...
Python随身听-2020-10-12-技术精选
🤩Python随身听-技术精选： /TurboWay/big_screen
👉数据大屏可视化
😎TOPICS: ``
⭐️STARS：375, 今日上升数↑:64
👉README：
big_screen
数据大屏可视化
功能
便利性工具, 结构简单, 直接传数据就可以实现数据大屏
安装
pip install -i https://pypi.tuna.tsinghua.edu.cn/simple flask
运行
python app.py;
地址：https://github.com/TurboWay/big_screen
🤩Python随身听-技术精选： /CorentinJ/Real-Time-Voice-Cloning
👉Clone a voice in 5 seconds to generate arbitrary speech in real-time
😎TOPICS:
deep-learning,pytorch,tensorflow,tts,voice-cloning,python⭐️STARS：19937, 今日上升数↑:98
👉README：
Real-Time Voice Cloning
This repository is an implementation of Transfer Learning from Speaker Verification to
Multispeaker Text-To-Speech Synthesis (SV2TTS) with a vocoder that works in real-time. Feel free to check my thesis if you're curious or if you're looking for info I haven't documented. Mostly I would recommend giving a quick look to the figures beyond the introduction.
SV2TTS is a three-stage deep learning framework that allows to create a numerical representation of a voice from a few seconds of audio, and to use it to condition a text-to-speech model trained to generalize to new voices.
Video demonstration (click the picture):
Papers implemented
地址：https://github.com/CorentinJ/Real-Time-Voice-Cloning
🤩Python随身听-技术精选： /Asabeneh/30-Days-Of-Python
👉30 days of Python programming challenge is a step by step guide to learn Python programming language in 30 days.
😎TOPICS:
30-days-of-python,python⭐️STARS：2130, 今日上升数↑:117
👉README：
🐍 30 Days Of Python
地址：https://github.com/Asabeneh/30-Days-Of-Python
🤩Python随身听-技术精选： /jackfrued/Python-100-Days
👉Python - 100天从新手到大师
😎TOPICS: ``
⭐️STARS：93832, 今日上升数↑:305
👉README：
Python - 100天从新手到大师
Python应用领域和职业发展分析
简单的说，Python是一个“优雅”、“明确”、“简单”的编程语言。
Python在以下领域都有用武之地。
地址：https://github.com/jackfrued/Python-100-Days
🤩Python随身听-技术精选： /iperov/DeepFaceLab
👉DeepFaceLab is the leading software for creating deepfakes.
😎TOPICS:
faceswap,face-swap,deep-learning,deeplearning,deep-neural-networks,deepfakes,deepface,deep-face-swap,fakeapp,neural-networks,neural-nets,deepfacelab,creating-deepfakes,arxiv⭐️STARS：20194, 今日上升数↑:46
👉README：
DeepFaceLab
https://arxiv.org/abs/2005.05535
the leading software for creating deepfakes
More than 95% of deepfake videos are created with DeepFaceLab.
DeepFaceLab is used by such popular youtube channels as
|---|---|
|---|---|---|
|---|---|---|
What can I do using DeepFaceLab?
Replace the face
De-age the face
<img src="doc/...
地址：https://github.com/iperov/DeepFaceLab
🤩Python随身听-技术精选： /deepfakes/faceswap
👉Deepfakes Software For All
😎TOPICS:
faceswap,face-swap,deep-learning,deeplearning,deep-neural-networks,deepfakes,deepface,deep-face-swap,fakeapp,neural-networks,neural-nets,openfaceswap,myfakeapp,machine-learning⭐️STARS：32667, 今日上升数↑:44
👉README：
deepfakes_faceswap
FaceSwap is a tool that utilizes deep learning to recognize and swap faces in pictures and videos.
Jennifer Lawrence/Steve Buscemi FaceSwap using the Villain model
Make sure you check out INSTALL.md before getting started.
...
地址：https://github.com/deepfakes/faceswap
🤩Python随身听-技术精选： /ymcui/Chinese-BERT-wwm
👉Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）
😎TOPICS:
chinese-bert,tensorflow,pytorch,bert,nlp,roberta,bert-wwm,bert-wwm-ext,roberta-wwm,rbt⭐️STARS：3947, 今日上升数↑:24
👉README：
中文说明 | English
在自然语言处理领域中，预训练语言模型（Pre-trained Language Models）已成为非常重要的基础技术。为了进一步促进中文信息处理的研究发展，我们发布了基于全词遮罩（Whole Word Masking）技术的中文预训练模型BERT-wwm，以及与此技术密切相关的模型：BERT-wwm-ext，RoBERTa-wwm-ext，RoBERTa-wwm-ext-large, RBT3, RBTL3。Pre-Training with Whole Word Masking for Chinese BERT
Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Ziqing Yang, Shijin Wang, Guoping Hu
本项目基于谷歌官方BERT：https://github.com/google-research/bert
其他相关资源：
地址：https://github.com/ymcui/Chinese-BERT-wwm
🤩Python随身听-技术精选： /google-research/bert
👉TensorFlow code and pre-trained models for BERT
😎TOPICS:
nlp,google,natural-language-processing,natural-language-understanding,tensorflow⭐️STARS：25194, 今日上升数↑:41
👉README：
BERT
***** New March 11th, 2020: Smaller BERT Models *****
This is a release of 24 smaller BERT models (English only, uncased, trained with WordPiece masking) referenced in Well-Read Students Learn Better: On the Importance of Pre-training Compact Models.
We have shown that the standard BERT recipe (including model architecture and training objective) is effective on a wide range of model sizes, beyond BERT-Base and BERT-Large. The smaller BERT models are intended for environments with restricted computational resources. They can be fine-tuned in the same manner as the original BERT models. However, they are most effective in the context of knowledge distillation, where the fine-tuning labels are produced by a larger and more accurate teacher.
Our goal is to enable research in institutions with fewer computational resources and encourage the community to seek directions of innovation alternative to increasing model capacity.
You can download all 24 fro...
地址：https://github.com/google-research/bert
🤩Python随身听-技术精选： /521xueweihan/HelloGitHub
👉:octocat: Find pearls on open-source seashore 分享 GitHub 上有趣、入门级的开源项目
😎TOPICS:
github,hellogithub,python,awesome⭐️STARS：33982, 今日上升数↑:74
👉README：
中文 | English
HelloGitHub 分享 GitHub 上有趣、入门级的开源项目。
兴趣是最好的老师，这里能够帮你找到编程的兴趣！
🤩Python随身听-技术精选： /ultralytics/yolov5
👉YOLOv5 in PyTorch > ONNX > CoreML > TFLite
😎TOPICS:
yolov3,yolov4,yolov5,object-detection,pytorch,onnx,coreml,ios,tflite,yolo⭐️STARS：5368, 今日上升数↑:65
👉README：
This repository represents Ultralytics open-source research into future object detection methods, and incorporates our lessons learned and best practices evolved over training thousands of models on custom client datasets with our previous YOLO repository https://github.com/ultralytics/yolov3. All code and models are under active development, and are subject to modification or deletion without notice. Use at your own risk.
地址：https://github.com/ultralytics/yolov5
🤩Python随身听-技术精选： /donnemartin/system-design-primer
👉Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
😎TOPICS:
programming,development,design,design-system,system,design-patterns,web,web-application,webapp,python,interview,interview-questions,interview-practice⭐️STARS：108953, 今日上升数↑:195
👉README：
*English ∙ 日本語 ∙ 简体中文 ∙ 繁體中文 | العَرَبِيَّة ∙ বাংলা ∙ Português do Brasil ∙ Deutsch ∙ ελληνικά ∙ עברית ∙ Italiano ∙ 한국어 ∙ فارسی ∙ Polski ∙ русский язык ∙ Español ∙ [...
地址：https://github.com/donnemartin/system-design-primer
🤩Python随身听-技术精选： /theAIGuysCode/yolov4-deepsort
👉Object tracking implemented with YOLOv4, DeepSort, and TensorFlow.
😎TOPICS:
yolov4,yolov4-deepsort,deep-sort,object-tracker,tensorflow,object-tracking,object-detection⭐️STARS：134, 今日上升数↑:52
👉README：
yolov4-deepsort
Object tracking implemented with YOLOv4, DeepSort, and TensorFlow. YOLOv4 is a state of the art algorithm that uses deep convolutional neural networks to perform object detections. We can take the output of YOLOv4 feed these object detections into Deep SORT (Simple Online and Realtime Tracking with a Deep Association Metric) in order to create a highly accurate object tracker.
Demo of Object Tracker on Persons
Demo of Object Tracker on Cars
Getting Started
To get started, install the proper dependencies either via Anaconda or Pip. I recommend Anaconda route for people using a GPU as it configures CUDA toolkit version for you.
Conda (Recommended)
Tensorflow CPU
conda env create -f conda-cpu.yml
conda activate yolov4-cpu
Tensorflow GPU
conda env create -f conda-gpu.yml
conda activate yolov4-gpu
Pip
(TensorFlow 2 packages require a pip version >1...
地址：https://github.com/theAIGuysCode/yolov4-deepsort
🤩Python随身听-技术精选： /numpy/numpy
👉The fundamental package for scientific computing with Python.
😎TOPICS:
numpy,python⭐️STARS：15104, 今日上升数↑:35
👉README：
NumPy is the fundamental package needed for scientific computing with Python.
It provides:
地址：https://github.com/numpy/numpy
🤩Python随身听-技术精选： /yunjey/pytorch-tutorial
👉PyTorch Tutorial for Deep Learning Researchers
😎TOPICS:
deep-learning,pytorch-tutorial,neural-networks,pytorch⭐️STARS：18304, 今日上升数↑:29
👉README：
This repository provides tutorial code for deep learning researchers to learn PyTorch. In the tutorial, most of the models were implemented with less than 30 lines of code. Before starting this tutorial, it is recommended to finish Official Pytorch Tutorial.
Table of Contents
1. Basics
地址：https://github.com/yunjey/pytorch-tutorial
🤩Python随身听-技术精选： /koaning/human-learn
👉Natural Intelligence is still a pretty good idea.
😎TOPICS:
scikit-learn,machine-learning,benchmark⭐️STARS：155, 今日上升数↑:65
👉README：
Human Learning
Project Goal
Back in the old days, it was common to write rule-based systems. Systems that do;
Nowadays, it's much more fashionable to use machine learning instead. Something like;
We started wondering if we might have lost something in this transition. Sure,
machine learning covers a lot of ground but it is also capable of making bad
decision. We've also reached a stage of hype that folks forget that many
classification problems can be handled by natural intelligence too.
This package contains scikit-learn compatible tools that should make it easier
to construct and benchmark rule based systems that are designed by humans. You
can also use it in combination with ML models.
Installation
You can install this tool via
pip.python -m pip install human-learn
Documentation
Detailed documentation of this tool can be found [here](https://koaning.github.io/huma...
地址：https://github.com/koaning/human-learn
🤩Python随身听-技术精选： /jina-ai/jina
👉An easier way to build neural search in the cloud
😎TOPICS:
jina,neural-search,cloud-native,python,deep-learning,nlp,computer-vision,video-search,image-search,semantic-search,microservice,machine-learning,tensorflow,pytorch,transformers,docker,hacktoberfest,zmq,cython⭐️STARS：1283, 今日上升数↑:18
👉README：
English • 日本語 • Français • Deutsch • Русский язык • 中文
Website • Docs • Examples • Hub (beta) • Dashboard (beta) • Jinabox (beta) • 地址：https://github.com/jina-ai/jina
🤩Python随身听-技术精选： /Rapptz/discord.py
👉An API wrapper for Discord written in Python.
😎TOPICS:
discord,discord-api,python,python-3⭐️STARS：5669, 今日上升数↑:24
👉README：
discord.py
.. image:: https://discord.com/api/guilds/336642139381301249/embed.png
:target: https://discord.gg/r3sSKJJ
:alt: Discord server invite
.. image:: https://img.shields.io/pypi/v/discord.py.svg
:target: https://pypi.python.org/pypi/discord.py
:alt: PyPI version info
.. image:: https://img.shields.io/pypi/pyversions/discord.py.svg
:target: https://pypi.python.org/pypi/discord.py
:alt: PyPI supported Python versions
A modern, easy to use, feature-rich, and async ready API wrapper for Discord written in Python.
Key Features
asyncandawait.Installing
Python 3.5.3 or higher is required
To install the library without full voice support, you can just run the following command:
.. code:: sh
Otherwise to get voice supp...
地址：https://github.com/Rapptz/discord.py
🤩Python随身听-技术精选： /Dod-o/Statistical-Learning-Method_Code
👉手写实现李航《统计学习方法》书中全部算法
😎TOPICS:
machine-learning-algorithms,code,statistical-learning-method⭐️STARS：6246, 今日上升数↑:27
👉README：
前言
力求每行代码都有注释，重要部分注明公式来源。具体会追求下方这样的代码，学习者可以照着公式看程序，让代码有据可查。
如果时间充沛的话，可能会试着给每一章写一篇博客。先放个博客链接吧：传送门。
注：其中Mnist数据集已转换为csv格式，由于体积为107M超过限制，改为压缩包形式。下载后务必先将Mnist文件内压缩包直接解压。
另：有意向为这个repo补充第二版无监督部分的大佬下拉到最下方联系我～只要求注释完善即可。我们可以成为好朋友一起冲鸭！！！
实现
第二章 感知机：
博客：统计学习方法|感知机原理剖析及实现
实现：perceptron/perceptron_dichotomy.py
第三章 K近邻：
博客：统计学习方法|K近邻原理剖析及实现
实现：KNN/KNN.py
第四章 朴素贝叶斯：
博客：统计学习方法|朴素贝叶斯原理剖析及实现
实现：NaiveBayes/NaiveBayes.py
第五章 决策树：
博客：[统计学习方法|决策树原理剖析及实现](http://www.pkudodo.com/2018/11/30/...
地址：https://github.com/Dod-o/Statistical-Learning-Method_Code
🤩Python随身听-技术精选： /python-telegram-bot/python-telegram-bot
👉We have made you a wrapper you can't refuse
😎TOPICS:
python,telegram,bot,chatbot,framework,hacktoberfest⭐️STARS：11950, 今日上升数↑:36
👉README：
.. image:: https://github.com/python-telegram-bot/logos/blob/master/logo-text/png/ptb-logo-text_768.png?raw=true
:align: center
:target: https://python-telegram-bot.org
:alt: python-telegram-bot Logo
We have made you a wrapper you can't refuse
We have a vibrant community of developers helping each other in our
Telegram group <https://telegram.me/pythontelegrambotgroup>_. Join us!Stay tuned for library updates and new releases on our
Telegram Channel <https://telegram.me/pythontelegrambotchannel>_... image:: https://img.shields.io/pypi/v/python-telegram-bot.svg
:target: https://pypi.org/project/python-telegram-bot/
:alt: PyPi Package Version
.. image:: https://img.shields.io/pypi/pyversions/python-telegram-bot.svg
:target: https://pypi.org/project/python-telegram-bot/
:alt: Supported Python versions
.. image:: https://cpu.re/static/python-telegram-bot/downloads.svg
:target: https://www.cpu.re/static/python-telegram-bot/downloads-by-python-version.txt
:alt: PyPi Package ...
地址：https://github.com/python-telegram-bot/python-telegram-bot
🤩Python随身听-技术精选： /hamuchiwa/AutoRCCar
👉OpenCV Python Neural Network Autonomous RC Car
😎TOPICS: ``
⭐️STARS：2878, 今日上升数↑:91
👉README：
AutoRCCar
Python3 + OpenCV3
See self-driving in action
This project builds a self-driving RC car using Raspberry Pi, Arduino and open source software. Raspberry Pi collects inputs from a camera module and an ultrasonic sensor, and sends data to a computer wirelessly. The computer processes input images and sensor data for object detection (stop sign and traffic light) and collision avoidance respectively. A neural network model runs on computer and makes predictions for steering based on input images. Predictions are then sent to the Arduino for RC car control.
Setting up environment with Anaconda
miniconda(Python3)on your computerauto-rccarenvironment with all necessary libraries for this project地址：https://github.com/hamuchiwa/AutoRCCar
🤩Python随身听-技术精选： /NVlabs/stylegan2-ada
👉StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation
😎TOPICS: ``
⭐️STARS：212, 今日上升数↑:86
👉README：
StyleGAN2 with adaptive discriminator augmentation (ADA)
— Official TensorFlow implementation
Training Generative Adversarial Networks with Limited Data
Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila
https://arxiv.org/abs/2006.06676
Abstract: *Training generative adversarial networks (GAN) using too little data typically leads to discriminator overfitting, causing training to diverge. We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes. The approach does not require changes to loss functions or network architectures, and is applicable both when training from scratch and when fine-tuning an existing GAN on another dataset. We demonstrate, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images. We expect this to open up new application domains for GANs. We a...
地址：https://github.com/NVlabs/stylegan2-ada
🤩Python随身听-技术精选： /apachecn/AiLearning
👉AiLearning: 机器学习 - MachineLearning - ML、深度学习 - DeepLearning - DL、自然语言处理 NLP
😎TOPICS:
fp-growth,apriori,mahchine-leaning,naivebayes,svm,adaboost,kmeans,svd,pca,logistic,regression,recommendedsystem,sklearn,scikit-learn,nlp,deeplearning,python,dnn,lstm,rnn⭐️STARS：27304, 今日上升数↑:51
👉README：
AI learning
网站地址
地址A: xxx (欢迎留言，我们完善补充)
下载
Docker
docker pull apachecn0/ailearning
docker run -tid -p :80 apachecn0/ailearning
访问 http://localhost:{port} 查看文档
PYPI
pip install apachecn-ailearning
apachecn-ailearning
访问 http://localhost:{port} 查看文档
NPM
npm install -g ailearning
ailearning
...
地址：https://github.com/apachecn/AiLearning
🤩Python随身听-技术精选： /dennybritz/reinforcement-learning
👉Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.
😎TOPICS: ``
⭐️STARS：15404, 今日上升数↑:112
👉README：
Overview
This repository provides code, exercises and solutions for popular Reinforcement Learning algorithms. These are meant to serve as a learning tool to complement the theoretical materials from
Each folder in corresponds to one or more chapters of the above textbook and/or course. In addition to exercises and solution, each folder also contains a list of learning goals, a brief concept summary, and links to the relevant readings.
All code is written in Python 3 and uses RL environments from OpenAI Gym. Advanced techniques use Tensorflow for neural network implementations.
Table of Contents
地址：https://github.com/dennybritz/reinforcement-learning
🤩Python随身听-技术精选： /simoninithomas/Deep_reinforcement_learning_Course
👉Implementations from the free course Deep Reinforcement Learning with Tensorflow and PyTorch
😎TOPICS:
deep-reinforcement-learning,qlearning,deep-learning,tensorflow-tutorials,tensorflow,ppo,a2c,actor-critic,deep-q-network,deep-q-learning,pytorch,unity⭐️STARS：2557, 今日上升数↑:92
👉README：
Deep Reinforcement Learning Course
Syllabus
Part 1: Introduction to Deeep Reinforcement Learning
📜 ARTICLE Introduction to Deep Reinforcement Learning
📹 VIDEO Introduction to Deep Reinforcement Learning
Part 2: Q-learning with FrozenLake
📜 [ARTICLE](h...
地址：https://github.com/simoninithomas/Deep_reinforcement_learning_Course
🤩Python随身听-技术精选： /AtsushiSakai/PythonRobotics
👉Python sample codes for robotics algorithms.
😎TOPICS:
python,robotics,algorithm,path-planning,control,animation,localization,slam,cvxpy,ekf,autonomous-vehicles,autonomous-driving,mapping,autonomous-navigation,robot⭐️STARS：10331, 今日上升数↑:22
👉README：
PythonRobotics
Python codes for robotics algorithm.
Table of Contents
地址：https://github.com/AtsushiSakai/PythonRobotics
🤩Python随身听-技术精选： /atomic14/diy-alexa
👉Command recognition research
😎TOPICS: ``
⭐️STARS：59, 今日上升数↑:21
👉README：
DIY Alexa with the ESP32
Want to build your own Alexa? All you will need is an ESP32 and Microphone board.
Demo video and code walkthrough is available here on YouTube
I'm using a microphone breakout board that I've built myself based around the ICS-43434 - but any microphone board will work. The code has been written so that you can either use an I2S microphone or an analogue microphone using the built-in ADC.
I would recommend using an I2S microphone if you have one as they have a lot better noise characteristics.
My board is available on eBay and Tindie
Other I2S microphones are equally suitable. Boards based around the INMP441 work very well.
Wake word detection is carried out using a model train...
地址：https://github.com/atomic14/diy-alexa
🤩Python随身听-技术精选： /Pierian-Data/Complete-Python-3-Bootcamp
👉Course Files for Complete Python 3 Bootcamp Course on Udemy
😎TOPICS: ``
⭐️STARS：12372, 今日上升数↑:31
👉README：
Complete-Python-3-Bootcamp
Course Files for Complete Python 3 Bootcamp Course on Udemy
Get it now for ...
地址：https://github.com/Pierian-Data/Complete-Python-3-Bootcamp
🤩Python随身听-技术精选： /AIZOOTech/FaceMaskDetection
👉开源人脸口罩检测模型和数据 Detect faces and determine whether people are wearing mask.
😎TOPICS:
detection,pytorch,caffe⭐️STARS：1176, 今日上升数↑:15
👉README：
FaceMaskDetection
中文版 | English version
We open source all the popular deep learning frameworks' model and inference code to do face mask detection.
** Detect faces and determine whether they are wearing mask. **
** First of all, we hope the people in the world defeat COVID-2019 as soon as possible. Stay strong, all the countries in the world.**
We make face mask detection models with five mainstream deep learning frameworks （PyTorch、TensorFlow、Keras、MXNet和caffe） open sourced, and the corresponding inference codes.
We published 7959 images to train the models. The dataset is composed of WIDER Face and MAFA, we verified some wrong annotations. You can download here from Google drive, if you can not vis...
地址：https://github.com/AIZOOTech/FaceMaskDetection
🤩Python随身听-技术精选： /fastai/fastbook
👉The fastai book, published as Jupyter Notebooks
😎TOPICS:
notebooks,fastai,deep-learning,machine-learning,data-science,python,book⭐️STARS：9644, 今日上升数↑:47
👉README：
English / Korean
The fastai book
These notebooks cover an introduction to deep learning, fastai, and PyTorch. fastai is a layered API for deep learning; for more information, see the fastai paper. Everything in this repo is copyright Jeremy Howard and Sylvain Gugger, 2020 onwards.
These notebooks are used for a MOOC and form the basis of this book, which is currently available for purchase. It does not have the same GPL restrictions that are on this draft.
The code in the notebooks and python
.pyfiles is covered by the GPL v3 license; see the LICENSE file for details.The remainder (including all markdown cells in the notebooks and other prose) is not licensed for any redistribution or change of format or medium, other than making copies of the notebooks or forking this repo...
地址：https://github.com/fastai/fastbook
🤩Python随身听-技术精选： /ageron/handson-ml
👉A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in python using Scikit-Learn and TensorFlow.
😎TOPICS:
tensorflow,scikit-learn,machine-learning,python,deep-learning,neural-network,ml,distributed,jupyter-notebook⭐️STARS：21236, 今日上升数↑:22
👉README：
Machine Learning Notebooks
This project aims at teaching you the fundamentals of Machine Learning in
python. It contains the example code and solutions to the exercises in my O'Reilly book Hands-on Machine Learning with Scikit-Learn and TensorFlow:
Simply open the Jupyter notebooks you are interested in:
地址：https://github.com/ageron/handson-ml
🤩Python随身听-技术精选： /CoreyMSchafer/code_snippets
👉None
😎TOPICS: ``
⭐️STARS：5848, 今日上升数↑:22
👉README：
code_...
地址：https://github.com/CoreyMSchafer/code_snippets
🤩Python随身听-技术精选： /stefan-jansen/machine-learning-for-trading
👉Code and resources for Machine Learning for Algorithmic Trading, 2nd edition.
😎TOPICS:
machine-learning,trading,investment,finance,data-science,investment-strategies,artificial-intelligence,trading-strategies,deep-learning,synthetic-data,ml4t-workflow,trading-agent⭐️STARS：1351, 今日上升数↑:11
👉README：
ML for Trading - 2nd Edition
This book aims to show how ML can add value to algorithmic trading strategies in a practical yet comprehensive way. It covers a broad range of ML techniques from linear regression to deep reinforcement learning and demonstrates how to build, backtest, and evaluate a trading strategy driven by model predictions.
In four parts with 23 chapters plus an appendix, it covers on over 800 pages:
地址：https://github.com/stefan-jansen/machine-learning-for-trading
🤩Python随身听-技术精选： /czy36mengfei/tensorflow2_tutorials_chinese
👉tensorflow2中文教程，持续更新(当前版本:tensorflow2.0)，tag: tensorflow 2.0 tutorials
😎TOPICS: ``
⭐️STARS：6282, 今日上升数↑:16
👉README：
tensorflow2_tutorials_chinese
tensorflow2中文教程，持续更新（不定期更新）
tensorflow 2.0 正式版已上线， 后面将持续根据TensorFlow2的相关教程和学习资料。
最新tensorflow教程和相关资源，请关注微信公众号：DoitNLP，
后面我会在DoitNLP上，持续更新深度学习、NLP、Tensorflow的相关教程和前沿资讯，它将成为我们一起学习tensorflow的大本营。
当前tensorflow版本：tensorflow2.0
最全Tensorflow 2.0 教程持续更新：
https://zhuanlan.zhihu.com/p/59507137
本教程主要由tensorflow2.0官方教程的个人学习复现笔记整理而来，并借鉴了一些keras构造神经网络的方法，中文讲解，方便喜欢阅读中文教程的朋友，tensorflow官方教程：https://www.tensorflow.org
TensorFlow 2.0 教程- Keras 快速入门
TensorFlow 2.0 教程-keras 函数api
TensorFlow 2.0 教程-使用keras训练模型
TensorFlow 2.0 教程-用keras构建自己的网络层
TensorFlow 2.0 教程-keras模型保存和序列化
TensorFlow 2.0 教程-eager模式
TensorFlow 2.0 教程-Variables
[TensorFlow 2.0 教程--AutoGraph](https://zhuanlan.zhihu.com/p/59482...
地址：https://github.com/czy36mengfei/tensorflow2_tutorials_chinese
🤩Python随身听-技术精选： /pytorch/vision
👉Datasets, Transforms and Models specific to Computer Vision
😎TOPICS:
computer-vision,machine-learning⭐️STARS：7408, 今日上升数↑:18
👉README：
torchvision
.. image:: https://travis-ci.org/pytorch/vision.svg?branch=master
:target: https://travis-ci.org/pytorch/vision
.. image:: https://codecov.io/gh/pytorch/vision/branch/master/graph/badge.svg
:target: https://codecov.io/gh/pytorch/vision
.. image:: https://pepy.tech/badge/torchvision
:target: https://pepy.tech/project/torchvision
.. image:: https://img.shields.io/badge/dynamic/json.svg?label=docs&url=https%3A%2F%2Fpypi.org%2Fpypi%2Ftorchvision%2Fjson&query=%24.info.version&colorB=brightgreen&prefix=v
:target: https://pytorch.org/docs/stable/torchvision/index.html
The torchvision package consists of popular datasets, model architectures, and common image transformations for computer vision.
Installation
We recommend Anaconda as Python package management system. Please refer to
pytorch.org <https://pytorch.org/>_for the detail of PyTorch (
torch) installation. The following is the correspondingtorchvisionversions andsupported Python versions.
+-------------------...
地址：https://github.com/pytorch/vision
🤩Python随身听-技术精选： /fengdu78/Data-Science-Notes
👉数据科学的笔记以及资料搜集
😎TOPICS: ``
⭐️STARS：4186, 今日上升数↑:20
👉README：
Data-Science-Notes
数据科学的笔记以及资料搜集，目前尚在更新，部分内容来源于github搜集。
0.math （数学基础）
1.python-basic （python基础）
2.numpy（numpy基础）
3.pandas（pandas基础）
4.scipy（scipy基础）
5.data-visualization（数据可视化基础，包含matplotlib和seaborn）
6.scikit-learn（scikit-learn基础）
7.machine-learning（机器学习基础）
8.deep-learning（深度学习基础）
9.feature-engineering（特征工程基础）
参考
地址：https://github.com/fengdu78/Data-Science-Notes
🤩Python随身听-技术精选： /ljpzzz/machinelearning
👉My blogs and code for machine learning. http://cnblogs.com/pinard
😎TOPICS:
machinelearning,algorithms,scikit-learn,reinforcementlearning⭐️STARS：4628, 今日上升数↑:14
👉README：
刘建平Pinard的博客配套代码
http://www.cnblogs.com/pinard 刘建平Pinard
之前不少朋友反应我博客中的代码都是连续的片段，不好学习，因此这里把文章和代码做一个整理。
代码有部分来源于网络，已加上相关方版权信息。部分为自己原创，已加上我的版权信息。
目录
机器学习基础与回归算法
机器学习分类算法
机器学习聚类算法
机器学习降维算法
机器学习集成学习算法
数学统计学
机器学习关联算法
机器学习推荐算法
深度学习算法
自然语言处理算法
强化学习算法
特征工程与算法落地
注意
2016-2017年写的博客使用的python版本是2.7， 2018年因为TensorFlow对Python3的一些要求，所以写博客使用的Python版本是3.6。少部分2016，2017年的博客代码无法找到，重新用Python3.6跑过上传，因此可能会出现和博客中代码稍有不一致的地方，主要涉及到print的语法和range的用法，若遇到问题，稍微修改即可跑通。
赞助我
强化学习文章与代码：:
|文章 | 代码|
强化学习（一）模型基础| 代码
强化学习（二）马尔科夫决策过程(MDP) | 无
强化学习（三）用动态规划（DP）求解 | 无
强化学习（四）用蒙特卡罗法（MC）求解 | 无
[强化学习（五）用时序差分法（TD）求解]...
地址：https://github.com/ljpzzz/machinelearning
🤩Python随身听-技术精选： /microsoft/computervision-recipes
👉Best Practices, code samples, and documentation for Computer Vision.
😎TOPICS:
machine-learning,computer-vision,deep-learning,python,jupyter-notebook,operationalization,kubernetes,azure,microsoft,data-science,tutorial,artificial-intelligence,image-classification,image-processing,similarity,object-detection,convolutional-neural-networks⭐️STARS：7076, 今日上升数↑:18
👉README：
Computer Vision
In recent years, we've see an extra-ordinary growth in Computer Vision, with applications in face recognition, image understanding, search, drones, mapping, semi-autonomous and autonomous vehicles. A key part to many of these applications are visual recognition tasks such as image classification, object detection and image similarity.
This repository provides examples and best practice guidelines for building computer vision systems. The goal of this repository is to build a comprehensive set of tools and examples that leverage recent advances in Computer Vision algorithms, neural architectures, and operationalizing such systems. Rather than creating implementions from scratch, we draw from existing state-of-the-art libraries and build additional utility around loading image data, optimizing and evaluating mo...
地址：https://github.com/microsoft/computervision-recipes
🤩Python随身听-技术精选： /practical-nlp/practical-nlp
👉Official Repository for 'Practical Natural Language Processing' by O'Reilly
😎TOPICS: ``
⭐️STARS：257, 今日上升数↑:83
👉README：
Practical Natural Language Processing
A Comprehensive Guide to Building Real-World NLP Systems
Sowmya Vajjala, Bodhisattwa P. Majumder, Anuj Gupta, Harshit Surana
Endorsed by:
Zachary Lipton, Sebastian Ruder, Marc Najork, Monojit Choudhury, Vinayak Hegde, Mengting Wan, Siddharth Sharma, & Ed Harris
Foreword by: Julian McAuley
Homepage: www.practicalnlp.ai
Published by O'Reilly Media, 2020
Book Structure
Please ...
地址：https://github.com/practical-nlp/practical-nlp
🤩Python随身听-技术精选： /fengdu78/lihang-code
👉《统计学习方法》的代码实现
😎TOPICS: ``
⭐️STARS：12580, 今日上升数↑:27
👉README：
《统计学习方法》第二版的代码实现
李航老师编写的《统计学习方法》全面系统地介绍了统计学习的主要方法，特别是监督学习方法，包括感知机、k近邻法、朴素贝叶斯法、决策树、逻辑斯谛回归与支持向量机、提升方法、em算法、隐马尔可夫模型和条件随机场等。除第1章概论和最后一章总结外，每章介绍一种方法。叙述从具体问题或实例入手，由浅入深，阐明思路，给出必要的数学推导，便于读者掌握统计学习方法的实质，学会运用。
《统计学习方法》可以说是机器学习的入门宝典，许多机器学习培训班、互联网企业的面试、笔试题目，很多都参考这本书。
今天我们将李航老师的《统计学习方法》第二版的代码进行了整理，并提供下载。
非常感谢各位朋友贡献的自己的笔记、代码！
2020年6月7日
代码目录
第1章 统计学习方法概论
第2章 感知机
第3章 k近邻法
第4章 朴素贝叶斯
第5章 决策树
第6章 逻辑斯谛回归
第7章 支持向量机
第8章 提升方法
第9章 EM算法及其推广
...
地址：https://github.com/fengdu78/lihang-code
🤩Python随身听-技术精选： /jaakkopasanen/AutoEq
👉Automatic headphone equalization from frequency responses
😎TOPICS: ``
⭐️STARS：2250, 今日上升数↑:13
👉README：
AutoEQ
TL;DR If you are here just looking to make your headphones sound better, find your headphone model in
results folder's recommended headphones list
and follow instructions in Usage section.
About This Project
AutoEQ is a project for equalizing headphone frequency responses automatically and it achieves this by parsing
frequency response measurements and producing equalization settings which correct the headphone to a neutral sound.
This project currently has over 2500 headphones covered in the
results folder.
See Usage for instructions how to use the results with
different equalizer softwares and
Results section for details about parameters and how the results were
obtained.
AutoEQ is not just a collection of automatically produced headphone equalization settings but also a tool for equalizing
headphones for yourself.
autoeq.pyprovides methods for reading data, equalizing it to a given targetresponse and saving the results for u...
地址：https://github.com/jaakkopasanen/AutoEq
🤩Python随身听-技术精选： /luwill/machine-learning-code-writing
👉Mathematical derivation and pure Python code implementation of machine learning algorithms.
😎TOPICS: ``
⭐️STARS：218, 今日上升数↑:13
👉README：
machine-learning-code-writing
Mathematical derivation and p...
地址：https://github.com/luwill/machine-learning-code-writing
The text was updated successfully, but these errors were encountered: