Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
tools:modellearner [2021/04/05 15:58]
superuser
tools:modellearner [2021/04/13 05:50] (current)
superuser
Line 2: Line 2:
 \\ \\
 === Getting started === === Getting started ===
-\\ 
 At the start of the program you will see window like this: At the start of the program you will see window like this:
 {{:​tools:​pasted:​20210405-144438.png}} {{:​tools:​pasted:​20210405-144438.png}}
Line 13: Line 12:
 ^ Model          ^ Classes ​      ^ ^ Model          ^ Classes ​      ^
 | **model144318.h5** ​   | 9    | | **model144318.h5** ​   | 9    |
 +| **model144750.h5** ​   | 9    |
 +| **model144753.h5** ​   | 14    |
 +| **model161221.h5** ​   | 9    |
 +| **model160985.h5** ​   | 14    |
  
 After specifying all the parameters press **Open** button After specifying all the parameters press **Open** button
 +\\ 
 +\\
 === Correction === === Correction ===
  
Line 30: Line 34:
 {{ :​tools:​screenshot_3.jpg?​nolink |}} {{ :​tools:​screenshot_3.jpg?​nolink |}}
  
-The image would be marked as exported.+The image would be marked as exported. ​So this image would be used to train the neural net. 
 +\\ 
 +\\
  
-Now press **Learn** button. A learning window will appear.+----
  
 === Learning === === Learning ===
 +Press **Learn** button. A learning window will appear
 +{{ :​tools:​screenshot_4.jpg?​nolink |}}
 +
 +Pick a test image. You will see raw output of the neural net. As you can see. Candy in the bottom middle appears cut in the same way we have seen in previous step.
 +
 +Now we need to train our network.
 +
 +To do that click the **Learn** button at the bottom right corner of the window.
 +Neural net will perform one learning iteration. You may perform more than one iteration. When you satisfied with the results - close the window.
 +{{ :​tools:​screenshot_5.jpg?​nolink |}}
 +
 +Now you can see how neural net behaves with loaded images
 +{{ :​tools:​screenshot_6.jpg?​nolink |}}
 +
 +But if you close the program now - you will loose all the changes. To save what neural net have learned you need to save the model.
 +To do so go to the **Learning** menu and press **Save model**
 +{{ :​tools:​screenshot_7.jpg?​nolink |}}
  • tools/modellearner.1617638299.txt.gz
  • Last modified: 2021/04/05 15:58
  • by superuser