Train3DMASCDialog
0
0
834
795
Dialog
-
Random Trees
-
<html><head/><body><p>OpenCV parameter</p><p>The maximum possible depth of the tree. That is the training algorithms attempts to split a node while its depth is less than maxDepth. The root node has zero depth. The actual depth may be smaller if the other termination criteria are met, and/or if the tree is pruned.</p><p>[default 25]</p></body></html>
max depth
-
<html><head/><body><p>The maximum possible depth of the tree.</p><p>That is the training algorithms attempts to split a node while its depth is less than maxDepth.</p><p>The root node has zero depth. The actual depth may be smaller if the other termination criteria are met and/or if the tree is pruned.</p></body></html>
1
25
-
<html><head/><body><p>OpenCV parameter</p><p>The number of trees in the forest!</p><p>[default 100]</p></body></html>
max tree count
-
The maximum number of iterations/elements
1
10000
10
100
-
<html><head/><body><p>OpenCV parameter</p><p>The size of the randomly selected subset of features at each tree node and that are used to find the best split(s). If you set it to 0 then the size will be set to the square root of the total number of features.</p><p>[default 0]</p></body></html>
active var count
-
<html><head/><body><p>The size of the randomly selected subset of features at each tree node and that are used to find the best split(s).</p><p>If you set it to 0 then the size will be set to the square root of the total number of features.</p><p>Default value is 0.</p></body></html>
-
<html><head/><body><p>OpenCV parameter</p><p>If the number of samples in a node is less than this parameter then the node will not be split.</p><p>[default 10]</p></body></html>
min sample count
-
If the number of samples in a node is less than this parameter then the node will not be split
1
10
-
Other parameters
-
Test data ratio
-
Ratio of input points used for evaluating the classification
%
0
99
20
-
<html><head/><body><p>You the existing feature for the training. If not checked, all features will be recalculated and the existing features will be overwritten.</p></body></html>
Use existing attributes
-
<html><head/><body><p>If checked : </p><p>* A directory is created near the parameter file, with name 3dmasc_yyyymmdd_HHhMM.</p><p>* A file 3dmasc_yyyymmdd_HHhMM.txt is created in this directory. </p><p>* Each time you train the classifier, the feature list and the classifier are stored and an entry is created in the trace file to save the overall accuracy.</p></body></html>
Keep traces
-
Keep attributes on completion
-
QFrame::StyledPanel
QFrame::Raised
-
Run
-
false
Save classifier
-
Close
runPushButton
closePushButton
savePushButton
-
0
0
Results
-
correct = 0/0 - accuracy = 0.0
-
Qt::ScrollBarAlwaysOn
false
false
QAbstractItemView::NoSelection
true
170
false
Feature
Importance
-
Export feature list
-
Scales
runPushButton
clicked()
Train3DMASCDialog
accept()
76
296
198
237