Description

Task 3B – Given an arena image print Animals and Habitats present in the arena
This document explains the problem to be solved in Task 3B and where to go next after you finish reading this document.
Problem Statement:
In this sub-task, you have to find Animals and Habitats from the given arena image and tag them in the image. You have to simultaneously produce an output of Animal/Habitat names and their locations on the command line.
This output will be a dictionary with:
1. keys being the positions/locations and
2. values being name of the Habitat or Animal.
Objective:
The main objective of this task is to integrate Task 2 and Task 3A. You have to use the previously trained models.
NOTE: You are only allowed to use libraries that we have installed and used in the previous tasks. Tensorflow or Keras should NOT be used.
Dataset: You can download the datasets for this task from following links:
1. Animals: Animals Dataset
2. Habitats: Habitat Dataset
You will only use these datasets to train your model.
TIP: You can use the dataset.py that we built in Task 1B for data loading.
Code Structure:
From now on, you will develop things with only little supervision and mentoring. But we still expect you to follow good programming standards and writing reusable, least redundant code wherever possible.
1. Since we are NOT giving you templates or anything it will have a great weightage from now on.
2. If you write tests now, it is even better.
3. Faster and smaller models in size will be ranked better.
Inside your project folder, you’ll have a main.py which will be the single most important entry point in your program.
Your main.py should expose these parameters. You can use argparse.