Coral Edge Accelerator
#
ML accelerator: Edge TPU ASIC (application-specific integrated circuit) designed by Google. Provides high-performance ML inferencing for TensorFlow Lite Models. USB 3.1 (gen 1) port and cable (SuperSpeed, 5Gb/s transfer speed) Dimensions: 30 x 65 x 8mm Price: USD74.99 in 2019, USD ＄ 60 in 2021, ￥ 740 @JD.com 0.5 watts/TOPS MAX 4 TOPS (int8), 2W. TF Lite + Debian only. Not available world wide Intel NCS2 Neural Compute Stick 2
#
Processor: Intel Movidius Myriad X Vision Processing Unit (VPU) USB 3.
...
“if you plan to use deep learning extensively (>150 hrs/mo), building your own deep learning workstation might be the right move.” [medium]
Baidu AI Studio (only for PaddlePaddle) Paperspace (cooperating with fast.ai) Google Colab (cooperating with fast.ai) vast.ai (C2C/P2P sharing, very cheap, a lot of time to init/load/unload) Kaggle (max 6h, good GPU but complex steps to use) MS Azure Amazon FloydHub (special CLI interface) ref:
CN intro: Paperspace vs. Colab, 2019 Best Deals in Deep Learning Cloud Providers, 2018 比较云GPU平台
Install (w/ GPU)
#
Install NV GPU driver and compatible CUDA version first, or install using pip together.
See PyTorch doc’s selector to find a compatible CUDA version.
Then use the cmd given by the selector to install PyTorch:
Tip: slow, tmux is suggested.
pip source:
#
pip install pytorch torchvision torchaudio cudatoolkit=11.1 pip binary:
#
Tip: the torch...whl file is > 3GB, which can be pre-downloaded using IDM/FDM etc.
...
see also: /dl-theory
Data
#
不得不赞！一个国内（可能）最好的海量 CV 数据集获取网站 Tutorials
#
图像分类任务中的 tricks 总结 (bak) 邱锡鹏 教授 2020 神经网络与深度学习
Keywords: CNN, RNN, Attention, Gaussian Mix., RBM, DBN, GAN, RL, TF, PyTorch: equation, pseudocode, exercise …
PDF, PPT, code, exercise & solution, etc. A collection of various DL deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks 2019 《TensorFlow 2.0 深度学习算法实战 2019》 (pdf version via Python 数据科学) ICCV 2019 教程: DL SOTA by MXNET & GluonCV, [github] [cn intor] CS294-158 Deep Unsupervised Learning, 14 weeks, slides & youtube, Spring 2019 (overview in CN) fast.
...
Note: tested with Ubuntu 16.04.1 using /root, for newer Ubuntu version (>= 17.04), check here.
Installation & Self-Tests
#
Use the installation script here.
//(Sunny only added conditional USE_CUDNN=1, the rest is the same as: ref. You may wanna set USE_CUDNN to 0, if no GPU is used).
Timing: 15min if everything goes well, while downloading speed 1~8MB/s.
Hello World (Mnist)
#
prepare data:
#
./data/mnist/get_mnist.sh # will download into .
...
See also:
TF practical part in do deep learning How to setup Docker and Nvidia-Docker 2.0 on Ubuntu 18.04 Install
#
Summary: install CUDA first, then TF.
ref TF 1.0 doc
ref nvidia doc, until step 3
requirements
#
64-bit Linux Python 2.7 or 3.3+ (3.5 used in this blog) NVIDIA CUDA 7.5 (8.0 if Pascal GPU) NVIDIA cuDNN >v4.0 (v5.1 recommended) NVIDIA GPU with compute capability >3.0 steps
#
1.
...
See also:
/dl-do-it
/ml-books (Learning Machine Learning, ML Books & Codes)
ML Interpratation, Comprehensibility & Causality
如何理解神经网络
#
理解 ANN 的关键 1: 加权求和、激活 新石器公园 - 你真的了解人工神经网络吗？一个视频看懂 2024 年的诺贝尔物理学奖（主要是最后一节 10 分钟） 理解 ANN 的关键 1: 加权求和、激活（上一条没看懂的可以看这个）【双语字幕】给宝宝看的神经网络书 理解 ANN 的关键 2: 子组件及其装配（特征提取） 3Blue1Brown -【中配】什么是神经网络：深度学习第 1 章 主要是前 10 分钟（另：英文原版） 研究生课程的小学数学化: 一小时从函数到 Transformer！一路大白话彻底理解 AI 原理 （令名： 【全 120 集】清华大佬终于把神经网络做成了动画片！2025 最新版 以上的综合（1.5h） 漫士沉思录 - 90 分钟！清华博士带你一口气搞懂人工智能和神经网络 ANN 数学拟合原理 啥都会一点的鼠鼠 - 五分钟秒懂神经网络原理，机器学习入门教程 ANN 数学梯度下降 啥都会一点的鼠鼠 - [保姆级教程]梯度下降手把手教学、excel 搭建神经网络 PyTorch 废话很多的教程（倍速过一遍前几个视频即可，信息密度比较低）黑马程序员 AI 大模型《神经网络与深度学习》全套视频课程，涵盖 Pytorch 深度学习框架、BP 神经网络、CNN 图像分类算法及 RNN 文本生成算法 Courses
#
// DataCamp.
...