All submissions will be evaluated with different metrics at the two phases of the competition.

- **Phase I**: This phase is hosted on Kaggle and will be using accuracy as the evaluation measure. 

- **Phase II**: This phase will run in an offline manner in which the qualifying participants from Phase I will submit their code scripts to be re-run on another set of private data under 6GB of GPU (RTX8000) memory limit and 9 hours of time constraints and the accuracy on the test set of this private data will be used for the final rankings.
The following machine configuration will be used for training your models/frameworks -
GPU : Quadro RTX 8000 
GPU Mem. Limit : 6GB
Total Time Limit : 9 Hours 
CPU Cores : 4
RAM : 32GB

## Submission File for Phase I

For each `image_id`, you should predict the corresponding image label in the `label` column

The file should be named submission.csv and contain the columns `image_id` and `label` in the following format:
~~~~
image_id,label
asdfghjklo,0
zxcvbnmlkj,1
~~~~

## Submission File for Phase II
Each qualifying team is required to submit scripts that will be run and evaluated on a private dataset. The details of qualification to Phase II and format of code scripts is specified in the **Description** tab.