blocks|key|3477399|text|您是否在Windows或OS+X上的虚拟机中运行它？如果是这样，那么它可能不会更快地工作。在虚拟机中(我使用的是Docker)，大多数时候你不能使用CUDA来渲染图像。我也有同样的问题，我打算先安装Ubuntu，然后再安装CUDA的NVidia驱动。目前，我正在渲染大约300kb的1080p图像，在8+8gb内存的英特尔核心i7上绘制一张图像需要15分钟。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|3477400|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

Do you run it in a Virtual Machine on Windows or OS X? If so, then it's probably not going to work any faster. In a Virtual Machine (I'm using Docker) you're most of the time not able to use CUDA to render the Images. I have the same problem and I'm going to try it by installing Ubuntu and then install the NVidia drivers for CUDA. At the moment I'm rendering 1080p images which are around 300kb and it takes 15 minutes to do 1 image on an Intel core i7 with 8gb of ram.

blocks|key|4946303|text|除非你能搬到一个更好的工作站/得到一个GPU，否则你将不得不调整图像的大小。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|4946304|img+=+PIL.Image.open('sky1024px.jpg')
img+=+np.float32(img.resize(+[int(0.5+*+s)+for+s+in+img.size]+))|code-block|syntax|javascript|4946305|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Unless you can move to a better workstation/get a GPU, you'll have to do with resizing the image.

<pre><code>img = PIL.Image.open('sky1024px.jpg')
img = np.float32(img.resize( [int(0.5 * s) for s in img.size] ))
</code></pre>

blocks|key|3477456|text|花1分钟来处理100kb的图像对于#deepdream来说是一个明智的周转时间，我们承认这些渲染具有令人难以置信的长烘焙时间。通常，实验研究软件会运行得太慢，渴望更快的计算机的未来。也就是说，有几种方法可以让你的设置执行得更快。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|3477457|3477458|线程！使用命令行参数增加线程计数。下面是在Caffe+How+to+enable+multithreading+with+Caffe?|unordered-list-item|offset|length|3477459|GPU！中启用多线程的一种方法安装CUDA，从CPU渲染切换到GPU渲染。如果您的服务器没有特殊的图形处理器，请尝试在亚马逊ec2上获取图形处理器实例。https://github.com/BVLC/caffe/wiki/Install-Caffe-on-EC2-from-scratch-(Ubuntu,-CUDA-7,-cuDNN)|3477460|3477461|entityMap|0|LINK|mutability|MUTABLE|url|https://stackoverflow.com/questions/31395729/how-to-enable-multithreading-with-caffe|1|https://github.com/BVLC/caffe/wiki/Install-Caffe-on-EC2-from-scratch-(Ubuntu,-CUDA-7,-cuDNN)^0|0|0|R|14|0|0|24|2K|1|0|0^^$0|@$1|2|3|4|5|6|7|U|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|V|8|@]|9|@]|A|$]]|$1|C|3|D|5|E|7|W|8|@]|9|@$F|X|G|Y|1|Z]]|A|$]]|$1|H|3|I|5|E|7|10|8|@]|9|@$F|11|G|12|1|13]]|A|$]]|$1|J|3|-4|5|6|7|14|8|@]|9|@]|A|$]]|$1|K|3|-4|5|6|7|15|8|@]|9|@]|A|$]]]|L|$M|$5|N|O|P|A|$Q|R]]|S|$5|N|O|P|A|$Q|T]]]]

Taking 1 minute to process a 100kb image is a sensible turnaround time for #deepdream, and we accept that these renders have an incredibly long baking time. Often, experimental research software will run too slow, hungry for a future of faster computers. That said, there are a couple ways that come to mind about making your setup execute faster.

<ul>
<li>Thread! Increase thread count with a command line argument. Here's one way to enable multi-threading in Caffe <a href="https://stackoverflow.com/questions/31395729/how-to-enable-multithreading-with-caffe">How to enable multithreading with Caffe?</a></li>
<li>GPU! Install CUDA and switch from CPU rendering to GPU rendering. If your server doesn't have a special GPU, try getting a GPU instance on amazon ec2. <a href="https://github.com/BVLC/caffe/wiki/Install-Caffe-on-EC2-from-scratch-(Ubuntu,-CUDA-7,-cuDNN)" rel="nofollow noreferrer">https://github.com/BVLC/caffe/wiki/Install-Caffe-on-EC2-from-scratch-(Ubuntu,-CUDA-7,-cuDNN)</a></li>
</ul>

blocks|key|3477472|text|根据经验，深度学习在计算和内存资源上都很困难。2+2gb内存的Core+Duo机器不是深度学习的好选择。请记住，许多该领域的先驱使用GTX+Titan卡进行了大量研究，因为在训练深度学习网络时，即使是在至强服务器上的CPU计算也非常慢。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|3477473|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

As a rule of thumb deep learning is hard on both compute and memory resources. A 2gb RAM Core Duo machine is just not a good choice for deep learning. Keep in mind a lot of the people who pioneered this field did much of their research using GTX Titan cards because CPU computation even on xeon servers is prohibitivly slow when training deep learning networks.

I managed to install #DeepDream in my server.

I have duo core and 2gb Ram. but it taking 1min to process a image of size 100kbp.

Any advice ?

DeepDream taking too long to render image

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

我设法在我的服务器上安装了#DeepDream。我有双核和2 2gb内存。但处理100kbp的图像需要1min。有什么建议吗？

问DeepDream渲染图像花费的时间太长
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问DeepDream渲染图像花费的时间太长EN