Deep Learning Bootcamp - Assignment 2 - Intermediate: Recognize Animals

Can you train a machine that would tell you the name of animal?



898 Submissions


Image recognition is a vital component in robotics such as driverless vehicles or domestic robots. Image recognition is also important in image search engines such as Google or Bing image search whereby you use rich image content to query for similar stuff. Like in Google photos where the system uses image recognition to categorize your images into things like cats, dogs, people and so on so that you can quickly search your albums for things like, “give me photos of my cat”, that's awesome.

Ever noticed how Facebook instantly recognises your friend’s face and asks you if you want to tag him in that photo? That’s image recognition. That’s just a basic example.


You are working on a robotics project where you are required to train your robot so that it can differentiate between 5 animals or birds. Your task here is to build a deep learning model that helps you recognize the animal or bird in images.

Evaluation Criteria

Submissions are evaluated using Accuracy Score.


How do we do it? 

Once you generate and submit the target variable predictions on the test dataset, your submissions will be compared with the true values of the target variable. 

The True or Actual values of the target variable are hidden on the DPhi platform so that we can evaluate your model's performance on unseen data. Finally, an accuracy score for your model will be generated and displayed.

Here is your Getting Started Notebook for Assignment 2
About the Data

The training dataset consists of about 9k medium quality animal images belonging to 5 categories: butterfly, sheep, cow, squirrel, elephant. - mucca (cow), pecora (sheep), elefante (elephant), farfalla (butterfly) and scoiattolo (squirrel). All the images have been collected from "google images" and have been checked by human. There is some erroneous data to simulate real conditions (eg. images taken by users of your app).

Dataset Link:

From the above link you will be able to download a zip file named ‘’. After you extract this zip file, you will get three files:

  1. train - contains five folders each folder containing images around 1000 to 2000 of those 5 five animals.  Each image has a unique name.
  2. test - contains 910 random images of those 5 animals whose predictions you are to submit on DPhi platform.
  3. Testing_set_animals.csv - this is the order of the predictions for each image that is to be submitted on the platform. Make sure the predictions you download are with their image’s filename in the same order as given in this file.



You need to choose a submission file.

File Format

Your submission should be in CSV format.


This file should have a header row called 'prediction'.
Please see the instructions to save a prediction file under the “Data” tab.

To participate in this challenge either you have to create a team of atleast None members or join some team