Problem statement

The government has been facing a long-standing issue of wild animals entering residential areas due to various reasons. It's of critical importance that if any such dangerous animal is encountered, the concerned authority should be notified immediately. Reptiles, especially snakes, are among the most dangerous animals and they often enter residential areas. 

Recently due to an incident of a youngster getting bitten by a snake, the government decided to install cameras at every corner of the road to detect snakes and other animals.

You have been hired as a Deep Learning engineer to create a sophisticated model that can detect the breed of a snake from its image.

Data description

This data set consists of the following two columns:

The data folder consists of two folders and two .csv files. The details are as follows:

• train: Contains 5508 images for 35 classes 
• test: Contains 2361 images
• train.csv: 5508 x 2
• test.csv: 2361 x 1

Submission format

You are required to write your predictions in a .csv file and upload it by clicking the Upload File button.

Sample submission

image_id,breed
a8b3ad1dde,nerodia-erythrogaster
8b492b973d,pantherophis-vulpinus
929b99ea92,thamnophis-sirtalis
bbac7385e2,pantherophis-obsoletus
ef776b1488,agkistrodon-contortrix

Evaluation metric

$score = {100* f1\_score(actual\_values,predicted\_values,average = 'weighted')}$

Note: To avoid any discrepancies in the scoring, ensure that all the index column (image_id) values in the submitted file match the values in the provided test.csv file.