The evaluation metric for this competition is [Categorical Accuracy](https://www.tensorflow.org/api_docs/python/tf/keras/metrics/CategoricalAccuracy), which calculates the percentage of predicted values (yPred) that match with actual values (yTrue) for one-hot labels.

The [CIFAR-10 dataset](https://www.cs.toronto.edu/~kriz/cifar.html) used in this competition is divided into 10 different classes and there are 50000 images for training and 10000 images for testing. The ground truth labels are available for both train and test sets and automatic scoring metric in this competition can only measure how accurately you predict the ground truth labels for test dataset from your submissions. Therefore, 100% accuracy can be reached by just submitting ground truth labels. For discouraging this unfair submissions, we want you to make submissions by using the [challenge\_test\_Keras](https://www.kaggle.com/code/maktas/challenge-test-keras) notebook publicly available. This notebook simply downloads your pre-trained network from a given url in Keras hdf5 format and evaluate the accuracy of your model and create the submission file. You just need to change the `url` assignment line at the end of the second code cell in this notebook. If you store your trained model in Goggle Drive, please ensure that you give the direct link instead of shared link. You can use [Google Drive Direct Link Generater](https://sites.google.com/site/gdocs2direct/) to convert the shared link into direct url link to use in the challenge\_test\_Keras notebook.

## Submission Format

Submission file should contain two columns: `Id` and `Category`. The first row in Id column is tagged as `Trained_Net_Path` and the first row in Category column is the url of your trained model in Keras hdf5 format. Starting from second row, `Id` column should contain the number of image in test set and `Category` column should contain the corresponding predicted label within [0-9] obtained from your trained model output. 

The url given in your submission will be used to check the validness of your submission. We will run the [challenge\_test\_Keras](https://www.kaggle.com/code/maktas/challenge-test-keras) notebook with the given url in your submission file and get the actual score for your submission. If there is any mismatch, we will regretfully invalidate your submission. We encourage all the participants to submit directly the output of their trained model in inference mode, instead of submitting known ground truth labels.