How to get the CK+ Dataset into a dataframe where one column is the image and the second column is the emotion (Is that even necessary?)

Question

I want to build a model for emotion classification and tbh I am struggling with the dataset. I am using CK+ since I read it'd be on industry standard. I don't know how to format it the right way so I can start working. The Dataset is formatted in the following way.

Anger (Folder)

File 1
File 2
...

Contempt (Folder)

File 3
File 4
...

I need the foldernames as labels for the files inside of the folder but don't really know how to get there.

score 0 · Accepted Answer · answered Sep 12 '22 at 15:28

You can load all your data in a tf.data.Dataset using the tf.keras.utils.image_dataset_from_directory function. Assuming that your Anger and Contempt folders are located in a directory named Parent you can do like this:

import tensorflow as tf
dataset = tf.keras.utils.image_dataset_from_directory('Parent')

You can then access the images and labels directly from the Dataset, for example like this:

iterator = dataset.as_numpy_iterator()
print(iterator.next())

How to get the CK+ Dataset into a dataframe where one column is the image and the second column is the emotion (Is that even necessary?)

1 Answers1