-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
7 changed files
with
15 additions
and
2 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,13 @@ | ||
# Emotion Detection scripts | ||
Dieser Ordner enthält das Skript "emotion_model.py" zum Training eines Convolutional Neural Networks mithilfe des Datasets FER2013 und der Sequential-Models von Tensorflow. | ||
|
||
Das aus dem Training entstandene CNN ist bereits gespeichert, einmal im .keras-Dateiformat, welches eigentlich Standard ist, und einmal im .h5-Legacy-Dateiformat, da das .keras-Dateiformat auf einem macOS-Gerät mit Apple Chip später zu Fehlern führt. | ||
|
||
## Modell neu trainieren | ||
|
||
Um das Convolutional Neural Network neu zu trainieren, lösche zunächst die beiden gespeicherten Modelle und füge das entpackte FER2013-Dataset (oder ein Dataset deiner Wahl) in den "archive"-Ordner hinzu. | ||
|
||
Das FER2013-Dataset ist nicht in diesem Repository enthalten, sondern ist hier als Download verfügbar: | ||
https://www.kaggle.com/datasets/msambare/fer2013 | ||
|
||
Nach diesem Schritt führe einfach das Skript "emotion_model.py" aus. Die beiden trainierten Modelle werden wieder in diesem Ordner gespeichert. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Binary file not shown.
Binary file not shown.
Binary file not shown.