The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with 6000 images per class. There are 50000 training images and 10000 test images.

The dataset is divided into five training batches and one test batch, each with 10000 images. The test batch contains exactly 1000 randomly-selected images from each class. The training batches contain the remaining images in random order, but some training batches may contain more images from one class than another. Between them, the training batches contain exactly 5000 images from each class.

The classes in the dataset are "airplane", "automobile", "bird", "cat", "deer", "dog", "frog", "horse", "ship", "truck".										

The classes are completely mutually exclusive. There is no overlap between automobiles and trucks. "Automobile" includes sedans, SUVs, things of that sort. "Truck" includes only big trucks. Neither includes pickup trucks.

For more information please visit https://www.cs.toronto.edu/~kriz/cifar.html

The Python version of CIFAR-10 dataset is used in this competition and converting the image format is handled in the script "cifar10_input.py".

## Files

*   **Dataset** - the folder containing train and test sets
*   **cifar10_input.py** - the Python script containing functions for converting dataset into image and various data augmentations. The codes are taken from [MadryLab](https://github.com/MadryLab/cifar10_challenge/blob/master/cifar10_input.py)
*   **model_challenge.py** - the Python script containing functions for defining the Deep Neural Network that should be trained in this challenge
*   **sample_submission.csv** - a sample submission file in the correct format

## Columns

*   `Id` - the id of the test image.
*   `Category` - predicted class number of the test image within [0,9]

The first row in `Id` column is tagged as `Trained_Net_Path` and the first row in `Category` is the url of the pre-trained model in Keras hdf5 format. This data will be used to check the validness of the submission. For further information please look at [Evaluation](https://www.kaggle.com/competitions/ai-training-challenge-1/overview/evaluation) section.