ZZ question: Solve the weka jvm outofmemory problem [solved]

Source: Internet
Author: User
Sender: finallyliuyu (lead donkey), email area: NLP
Question: solutions to weka jvm outofmemory Problems
Mail station: Shui mu Community (Sun Feb 20 10:36:12 2011), Station

We are using WEKA for text classification experiments (mainly focusing on measuring Feature Word selection)Algorithm).
Corpus: reteurs21578
Featurewords 100
Training set: 6950
Test Set: 2676
(In sparse data storage mode) ARFF file size: traincorpus. ARFF (538 K), testcorpus. ARFF (208 K) classifier uses SMO
The error "run outof memory" is returned.
The maxheap = 2048 m in runweka. INI is still invalid by referring to the method of one student ..
Do you have any other solutions?
I can see some methods to change the JVM size on the network, but I am not familiar with Java and do not know how to modify it. For detailed steps.
--
One NLP amateur

※Source: · shuimu community http://newsmth.net/· ~from: 159.226.20. *]

[Full text] [reply to article] [Author: finallyliuyu] [reply to author] [go to Forum] [go Back to Top] [shareSohu Weibo]

2 Sender: finallyliuyu (lead donkey), email area: NLP
Question: Re: solutions to weka jvm outofmemory Problems
Mailing site: shuimu community (Sun Feb 20 10:47:05 2011), within the site

I have uploaded my own data. I am very grateful for the help of my computer with WEKA kids shoes. In addition, I am skeptical that my WEKA installation is faulty. There are two types of WEKA on WEKA Official Website: one is built-in JVM and the other is without JVM. I have installed Java SDK on my computer before, so I chose not to bring JVM. In this way, the installed Java cannot be started on the shortcut menu.

[Mentioned in the finallyliuyu masterpiece :]
: We are using WEKA for text classification experiments (mainly focusing on measuring the advantages and disadvantages of Feature Word selection algorithms ).
: Corpus: reteurs21578
: Featurewords 100
:...................

--
One NLP amateur

※Source: · shuimu community http://newsmth.net/· ~from: 159.226.20. *]

Attachment: traincorpus. ARFF (538kb)

Attachment: testcorpus. ARFF (207kb)

[Full text] [reply to article] [Author: xwild] [reply to author] [go to Forum] [Back to Top] [shareSohu Weibo]

3 Sender: xwild (xwild), email area: NLP
Question: Re: solutions to weka jvm outofmemory Problems
Mailing site: shuimu community (Sun Feb 20 10:53:01 2011), within the site

You can try the WEKA command line and set the maximum memory.
[Mentioned in the finallyliuyu masterpiece :]
: We are using WEKA for text classification experiments (mainly focusing on measuring the advantages and disadvantages of Feature Word selection algorithms ).
: Corpus: reteurs21578
: Featurewords 100
:...................

--

※Source: · shuimu community http://newsmth.net/· ~from: 211.87.234. *]

[Full text] [reply to article] [Author: finallyliuyu] [reply to author] [go to Forum] [go Back to Top] [shareSohu Weibo]

4 Sender: finallyliuyu (lead donkey), email area: NLP
Question: Re: solutions to weka jvm outofmemory Problems
Mailing site: shuimu community (Sun Feb 20 11:28:23 2011), within the site

I am calling the WEKA Command Line Method in wekadoc, but it does not respond and does not go out of the classification process.
[Mentioned in the masterpiece xwild (xwild :]
: You can try the WEKA command line and set the maximum memory.

--
One NLP amateur

※Source: · shuimu community http://newsmth.net/· ~from: 159.226.20. *]

The image of this topic is as follows: wekasimplecli .jpg (11kb)

[Full text] [reply to article] [Author: xphan] [reply to author] [go to Forum] [Back to Top] [shareSohu Weibo]

5. Sender: xphan (dblue), email area: NLP
Question: Re: solutions to weka jvm outofmemory Problems
Mailing site: shuimu community (Sun Feb 20 16:43:30 2011), within the site

Java can use-XMS and-xmx in the command line to set the minimum and maximum memory, for example
Java-xms256m-xmx5 g...
However, when running in windows, the system also has restrictions on memory.

[Mentioned in the finallyliuyu masterpiece :]
: We are using WEKA for text classification experiments (mainly focusing on measuring the advantages and disadvantages of Feature Word selection algorithms ).
: Corpus: reteurs21578
: Featurewords 100
:...................

--

※Source: · shuimu community http://newsmth.net/· ~from: 125.39.171. *]

[Full text] [reply to article] [Author: fancyerii] [reply to author] [go to Forum] [go Back to Top] [shareSohu Weibo]

6. Sender: fancyerii (Meow's microphone), email area: NLP
Question: Re: solutions to weka jvm outofmemory Problems
Mailing site: shuimu community (Sun Feb 20 18:14:10 2011), within the site

You can debug the problem yourself.CodeOr the maillist sent to them is better.
[Mentioned in the finallyliuyu masterpiece :]
: We are using WEKA for text classification experiments (mainly focusing on measuring the advantages and disadvantages of Feature Word selection algorithms ).
: Corpus: reteurs21578
: Featurewords 100
:...................

--

※Source: · shuimu community http://newsmth.net/· ~from: 162.105.200. *]

[Full text] [reply to article] [Author: finallyliuyu] [reply to author] [go to Forum] [go Back to Top] [shareSohu Weibo]

7. Sender: finallyliuyu (lead donkey), email area: NLP
Question: Re: solutions to weka jvm outofmemory Problems
Mailing station: shuimu community (Mon Feb 21 21:14:03 2011), within the station

Thanks to xwild, this problem has been solved. The solution is as follows:
In the WEKA simplecli window, enter
Java-xmx 1024 m
Java WEKA. classifiers. Lazy. ibk-K 5-t data/traincorpus. ARFF-t data/testcorpus. ARFF-I
Here, KNN is used as an example to illustrate how to use the console to solve the WEKA memory limit problem.
References Chapter 1 Section 1 a command line primer of wekamanual provided by WEKA
Morgan. Kaufmann data mining chapter 1 Section 1 "the command line interface"

[Mentioned in the masterpiece xwild (xwild :]
: You can try the WEKA command line and set the maximum memory.

--
One NLP amateur

※source: · shuimu community http://newsmth.net/?from: 159.226.20. *]

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.