Recently a Deep Learning Classification Challenge was held on Hackerearth Platform.Using Pytorch I built a model deploying Resnet18(Transfer Learning) which predicts the dance-form and classifies the image among the 8 dance groups.
I got a Final Accuracy of 97.2% on the training set and the 88.889% on the validation set. Overall score obtained on Hackerearth is 73.02/100 which is among the top 250 in the leaderboard out of the 5.8k registered participants.
Problem statement📷
This International Dance Day, an event management company organized an evening of Indian classical dance performances to celebrate the rich, eloquent, and elegant art of dance. After the event, the company plans to create a microsite to promote and raise awareness among people about these dance forms. However, identifying them from images is a difficult task.
You are appointed as a Machine Learning Engineer for this project. Your task is to build a deep learning model that can help the company classify these images into eight categories of Indian classical dance.
Note
The eight categories of Indian classical dance are as follows:
-
Manipuri
-
Bharatanatyam
-
Odissi
-
Kathakali
-
Kathak
-
Sattriya
-
Kuchipudi
-
Mohiniyattam
Evaluation metric
Note: To avoid any discrepancies in the scoring, ensure all the index column (Image) values in the submitted file match the values in the provided test.csv file.
-
Made predictions on the Test Files
-
Uploaded them in .csv format
-
Submitted on HackerEarth, got a score of 73.02