Databases
StackOverflow2013
Postsdbo
POLIBSVM easy.py and grid.py doing worse that svm-train
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POLIBSVM easy.py and grid.py doing worse that svm-train
    primarykey
    data
    text
    <p>I am facing a problem with libsvm and I am hoping you can help me</p> <p>When I use svm-train.exe with default parameters like this...</p> <pre><code>svm-train dikomou svm-predict dikomou.t dikomou.model dikomou.t.predict </code></pre> <p>I get accuracy 84.72%</p> <p>When I use scaling [-1, 1] ,and same scaling for training and testing file like this....</p> <pre><code>svm-scale -l -1 -u 1 -s range1 dikomou &gt; dikomou.scale svm-scale -r range1 dikomou.t &gt; dikomou.t.scale svm-train dikomou.scale svm-predict dikomou.t.scale dikomou.scale.model dikomou.t.predict </code></pre> <p>I get less accuracy 81.94%</p> <p>If I do the scaling for 0 to 1 I get accuracy 87.5%</p> <p>So I keep the 0 to 1 scaling.</p> <p>BUT when I use <code>grid.py</code> with the 0 to 1 scaled data like this</p> <pre><code>grid.py dikomou.scale .. 8 0.0078125 84 ,25 $ ./svm-train -c 8 -g 0.0078125 dikomou.scale $ ./svm-predict dikomou.t.scale dikomou.scale.model dikomou.t.predict </code></pre> <p>I get cross validation rate 84.25% and total accuracy of 79.166% and best given c = 8 gamma= 0.0078125</p> <p>So the <code>grid.py</code> gives me less!!! accuracy than the one using the svm train with defaults. So I have two questions.</p> <ol> <li>How is this possible?? </li> <li>What are the default values of <code>c</code> and <code>gamma</code> the svm train uses?? (I cant find this clearly in the documentation. is gamma 1/number of features and c = 1?) and why the do better than when I use the <code>grid.py</code>?</li> </ol> <p><code>easy.py</code> also gives me worse results than the defaults. what can i do?</p>
    singulars
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PTQuestion
    1. USBenjamin
    1. USsotiraw
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. VO
      singulars
      1. POLIBSVM easy.py and grid.py doing worse that svm-train
      1. This table or related slice is empty.
      1. VTUpMod
    2. VO
      singulars
      1. POLIBSVM easy.py and grid.py doing worse that svm-train
      1. USuser2602256
      1. VTFavorite
    1. COI am also learning libsvm, In the file svm-train.c "-g gamma : set gamma in kernel function (default **1/num_features**)\n" "-r coef0 : set coef0 in kernel function (default **0**)\n"
      singulars
      1. POLIBSVM easy.py and grid.py doing worse that svm-train
      1. USAshish Negi
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload