ypwhs / Dl Engineer Guidebook
深度学习工程师生存指南
Stars: ✭ 399
Projects that are alternatives of or similar to Dl Engineer Guidebook
Echo
Python package containing all custom layers used in Neural Networks (Compatible with PyTorch, TensorFlow and MegEngine)
Stars: ✭ 126 (-68.42%)
Mutual labels: gitbook, deeplearning
Lost Nds Tv
The Lost Nintendo DS Television Output, brought back to life
Stars: ✭ 221 (-44.61%)
Mutual labels: hardware, homebrew
Blitz
Blitz is a 68030 based homebrew computer I designed over the course of nearly 3 years, starting in late 2017.
Stars: ✭ 31 (-92.23%)
Mutual labels: homebrew, hardware
Portrait Segmentation
Real-time portrait segmentation for mobile devices
Stars: ✭ 358 (-10.28%)
Mutual labels: deeplearning
Homebrew Autoupdate
🍹 An easy, convenient way to automatically update Homebrew.
Stars: ✭ 361 (-9.52%)
Mutual labels: homebrew
Salient Object Detection
This is tensorflow implementation for cvpr2017 paper "Deeply Supervised Salient Object Detection with Short Connections"
Stars: ✭ 397 (-0.5%)
Mutual labels: deeplearning
Dotfiles
paul's shell, git, etc config files. also homebrew, migration setup. good stuff.
Stars: ✭ 3,910 (+879.95%)
Mutual labels: homebrew
Invoice
增值税发票OCR识别,使用flask微服务架构,识别type:增值税电子普通发票,增值税普通发票,增值税专用发票;识别字段为:发票代码、发票号码、开票日期、校验码、税后金额等
Stars: ✭ 381 (-4.51%)
Mutual labels: deeplearning
Dotfiles
Setup and install scripts for a new machine + dotfiles for various apps. Linux, Mac, and Mac (Amazon specific) branches are included.
Stars: ✭ 382 (-4.26%)
Mutual labels: homebrew
Homebrew Bundle
📦 Bundler for non-Ruby dependencies from Homebrew, Homebrew Cask and the Mac App Store.
Stars: ✭ 3,940 (+887.47%)
Mutual labels: homebrew
Hackintosh Installer University
Open source tutorial & information collector for hackintosh installation.
Stars: ✭ 3,815 (+856.14%)
Mutual labels: hardware
Text summurization abstractive methods
Multiple implementations for abstractive text summurization , using google colab
Stars: ✭ 359 (-10.03%)
Mutual labels: deeplearning
Node Elgato Stream Deck
A Node.js library for interfacing with the Elgato Stream Deck.
Stars: ✭ 359 (-10.03%)
Mutual labels: hardware
Homebrew Cask
🍻 A CLI workflow for the administration of macOS applications distributed as binaries
Stars: ✭ 18,761 (+4602.01%)
Mutual labels: homebrew
Istio Handbook
Istio Handbook - Istio Service Mesh Advanced Practical(Istio 服务网格进阶实战) - https://jimmysong.io/istio-handbook
Stars: ✭ 374 (-6.27%)
Mutual labels: gitbook
Awesome Cybersecurity Datasets
A curated list of amazingly awesome Cybersecurity datasets
Stars: ✭ 380 (-4.76%)
Mutual labels: deeplearning
深度学习工程师生存指南
在线阅读:https://dl.ypw.io
项目地址:https://github.com/ypwhs/dl-engineer-guidebook
本书会讲述一个深度学习工程师所需的所有东西:
-
如何配置一台深度学习工作站?
- CPU
- 主板
- 显卡
- 硬盘
- 内存
- 电源
- 网卡
- 机箱
- 显示器
- 键盘鼠标
- 本地设备
- Windows、Linux 还是 macOS?
- Mac 对比
- 其他
- 触控板
- 机械键盘
- iPad Pro
- 路由器
- NAS
- 移动硬盘
- U盘
-
macOS 软件
- 终端
- 编辑器
- 浏览器
- 开发软件
- 实用工具
- 虚拟机
-
macOS 环境
- Homebrew
- oh my zsh
- 必备软件
- 终端
- 编辑器
- 浏览器
- 开发软件
- 实用工具
- 日常应用
- 必备命令
-
Python 环境
- Anaconda
- Python 库
-
Ubuntu 装机步骤
- 安装 Ubuntu
- 配置 ssh
- 配置 sudo 免密码 和 apt 源(推荐)
- 安装 oh my zsh 以及常用命令(推荐)
- 安装 NVIDIA 驱动、CUDA 和 cuDNN(分为 apt 和 run 两种安装方式)
- 安装 Anaconda 和 Python 库
-
Ubuntu 环境
- CUDA
- cuDNN
- TensorFlow
- PyTorch
- 必备命令
- curl
- tmux 与 iTerm2 结合使用
- screen 后台运行命令
-
常用 Linux 命令
- 文件查看
- 文件读写
- 打包压缩
- 权限管理
- 进程管理
- 磁盘管理
- 系统管理
- 系统监测
- 网络通信
-
CV 学习资源
- 公开课
- 网站
- 书籍
-
常用 CV 数据集
- 数据集使用方法
- MNIST
- CIFAR
- ImageNet
- VOC
- COCO
- CelebA
-
在 ImageNet 上表现出色的经典模型
- 预训练模型使用方法
- TensorFlow
- PyTorch
- 模型论文
- 预训练模型使用方法
-
如何使用 TensorBoard
- 安装
- 使用
- 创建文件对象(writer)
- 打开 TensorBoard 服务
- 可视化模型结构
- 记录标量(scalar)
- 记录多个标量(scalars)
- 记录图像(images)
- 完整代码
- 总结
-
离线 Python 环境
- 下载 conda 安装包
- 下载 pkg 文件和 whl 文件
- 启动 miniconda 容器
- 添加 conda 源(可选)
- 下载 pkg 文件
- 配置 pip 源(可选)
- 下载 whl 文件
- 在离线机器上进行安装
- 将离线包传到离线机器上
- 安装 conda
- 创建 Python 虚拟环境
- 安装 whl 库
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].