You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For some reason it appears my classifier is claiming the location of the behaviors is not the ground truth location to test the classifier, showing the same names for both classifier behaviors and those "unused"
how is this possible when you can clearly see the names are the same
Testing the selected Categorizer...
The behavior mode of the Categorizer: Non-interactive.
The type of the Categorizer: Animation Analyzer (Lv 3; Shape 32 X 32 X 1) + Pattern Recognizer (Lv 3; Shape 32 X 32 X 3).
The length of a behavior example in the Categorizer: 60 frames.
The Categorizer includes body parts in analysis with STD = 0.
The Categorizer includes background in analysis.
Behavior names in the Categorizer: ['away', 'crunch', 'grooming', 'immobile', 'jumping', 'licking', 'locomotion', 'rearing', 'tremors']
Unused behavior names in the Categorizer: ['away', 'tremors', 'jumping', 'locomotion', 'immobile', 'grooming', 'crunch', 'licking', 'rearing']
For some reason it appears my classifier is claiming the location of the behaviors is not the ground truth location to test the classifier, showing the same names for both classifier behaviors and those "unused"
how is this possible when you can clearly see the names are the same
Testing the selected Categorizer...
The behavior mode of the Categorizer: Non-interactive.
The type of the Categorizer: Animation Analyzer (Lv 3; Shape 32 X 32 X 1) + Pattern Recognizer (Lv 3; Shape 32 X 32 X 3).
The length of a behavior example in the Categorizer: 60 frames.
The Categorizer includes body parts in analysis with STD = 0.
The Categorizer includes background in analysis.
Behavior names in the Categorizer: ['away', 'crunch', 'grooming', 'immobile', 'jumping', 'licking', 'locomotion', 'rearing', 'tremors']
Unused behavior names in the Categorizer: ['away', 'tremors', 'jumping', 'locomotion', 'immobile', 'grooming', 'crunch', 'licking', 'rearing']
Hi,
The ground truth folder that is used for testing a Categorizer should be a folder containing subfolders. Each subfolder should be named precisely with the behavior names in the selected Categorizer to test. Each subfolder should contain behavior example pairs (avi + jpg) that belong to this behavior class.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Hi guys!
For some reason it appears my classifier is claiming the location of the behaviors is not the ground truth location to test the classifier, showing the same names for both classifier behaviors and those "unused"
how is this possible when you can clearly see the names are the same
Testing the selected Categorizer...
The behavior mode of the Categorizer: Non-interactive.
The type of the Categorizer: Animation Analyzer (Lv 3; Shape 32 X 32 X 1) + Pattern Recognizer (Lv 3; Shape 32 X 32 X 3).
The length of a behavior example in the Categorizer: 60 frames.
The Categorizer includes body parts in analysis with STD = 0.
The Categorizer includes background in analysis.
Behavior names in the Categorizer: ['away', 'crunch', 'grooming', 'immobile', 'jumping', 'licking', 'locomotion', 'rearing', 'tremors']
Unused behavior names in the Categorizer: ['away', 'tremors', 'jumping', 'locomotion', 'immobile', 'grooming', 'crunch', 'licking', 'rearing']
Beta Was this translation helpful? Give feedback.
All reactions