Loading
AIcrowd
Challenges
Organize a challenge FAQ Contact
Log In Sign Up
Back to AI Blitz #7
AI Blitz #7: Completed #educational Weight: 20.0
By  AIcrowd 
5288
390
15
268
Participate

🚨 Update in Test Dataset | 📥 Reminder to Download

🕵️ Introduction

You’re almost there! You can see the Red Planet in its glory. ☄️

But there’s one small problem — you need to know the planet’s rotation before you land. Luckily, you have a dataset of various Mars rotations. Using the ML approach, you can predict the Mars planet rotation!

Click here to access the starter kit.

 

💾 Dataset

The given dataset contains images of Mars's planet from different views. Each image contains its label the angle its is rotated from its axis. The range of angle of rotation is from 1-360. The dimensions of the images 256*256. The mars planet is only rotated on Z axis!

📁 Files

Following files are available in the resources section:

  • train.zip - (40000 samples) This zip file contains the mars planet images with images name corresponding to ImageID column of train.csv
  • train.csv - (40000 samples) This csv file contains the ImageID column corresponding to train.zip and label column as Mars Rotation which is between 0 to 360 degree.
  • val.zip - (4000 samples) This zip file contains the mars planet images with images name corresponding to ImageID column of val.csv
  • val.csv - (4000 samples) This csv file contains the ImageID column corresponding to val.zip and label column as Mars Rotation which is between 0 to 360 degree.
  • test.zip - (10000 samples) This zip file contains the mars planet images which will be used to evaluate the performance of the model.

🚀 Submission

  • Prepare a CSV containing ImageID column corresponding to test.zip and label column as Mars Planet Rotation.
  • The name of the above file should be submission.csv.
  • Sample submission format available at sample_submission.csv in the resources section.

Make your first submission here 🚀 !!

🖊 Evaluation Criteria

During evaluation Mean Squared Error will be used to test the efficiency of the model.

🔗 Links

📱 Contact