Dataset Info

This dataset is made from the original data in this competition. Every element is cut into smaller chunks of 256x256 dimensions.

Files

• .7z archive with the train images
• "train_sliced_DEFECTS.csv" contains only the images with defects and their according masks
• "train_sliced_ALL.csv" contains all the images (containing defects + no defects)

I kept the structure of the original data, so you can acquire all needed information to work with the current dataset from here:

Soon I will upload the sliced test images.