How to read a binary classification dataset

I’m working on a binary classification dataset. It has a single image folder which contains images for both train and test saved as eg. ‘id.jpg’. A ‘train.csv’ contains 2 columns- ‘image name(id.jpg)’ and ‘classification(0/1)’.

How do i write the python code for this dataset when the image is labelled in this way.

Can you please see the following threads


https://storage.googleapis.com/kaggle-forum-message-attachments/709960/14732/Creating_Training_Testing.py

Not sure but I guess they are discussing the same I hope.

1 Like

@4deep.prk wrt the above resource, should i convert images to pixel arrays and make a csv file with classification values. How do i make the dataset to work with CNN models