fast.ai Lesson 1: Deep Learning 2018

本文介绍如何在AWS上利用免费资源搭建基于Ubuntu 16的深度学习环境,并选择250GB存储空间,使用GPU提升计算效率,实现比CPU快约10倍的速度,适合实时翻译等任务。

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

10 free hours

run on AWS

 

 

 

 

 

 

 

 

click this one

 

 

 

 

click on new machine

 pick a region

choose linux ubuntu 16

  

250GB is preferred

 

 

 

 

 

 

 

 

 

 

ctrl shift v 

to paste your password

 

 

zoom in

 

takes an hour or so.

when it finishs running, you need to reboot your paperspace computer

 

 

 

 

 

 

double click the last line to copy the url

then you can  go and past it

 change local host into the true IP address

 

 

 

 

 

 

 

 

 

 

or hold on shift and press enter

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

no, don't follow this suggestion.

 

 

 

 

 

 

 

 

 

 

ML was invented by this man.

 

 

 

 

 

 

 

 

a function that can sovle all problems

 

 

 

 

 

 

 

 

 

 

 

 

 

 gpu is about 10 times faster than cpu

 gpu is also cheaper

 

 

 

 

 

 

 

 

 

 

 

 

real time translation

 

 

 

 

 

use DL to help combine human experties and what computers are good at

 

 

 

 

 

 

 

 

 

 

 

 

setosa.io/ev/image-kernels/ 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

draw a picture of what neural networks has learnt

 

 

 

 

 

 

 

 

 

 

just 3 layers is enouch to get some pretty rich behaviors

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

hit tab, and get a list of methods

 

 

 

hit shift tab tells you the arguments to the method

 

 

 

 

 

 

shift tab twice or three times and get a documentation window

 

 

 

 

 

 

 

 

 

look at the source code

 

 

 

 

 

press H 

 

 

 

 

stop the machine and see the connection is closed

 

转载于:https://www.cnblogs.com/ecoflex/p/8995592.html

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值