Update in evaluator 🥌

F1 is one of the most fast-paced sports. With cars averaging speeds in 240 kmph, a mild change in terrain, and things get messy. Often, this ends up in cars spinning out of the track or colliding with others on the track. 😱

In a high-speed situation, how does one quickly identify the car and send necessarily roadside assistance? Your first puzzle is to detect an F1 car. Given an image, are you quickly able to identify the car? This simple object classification will get you warmed up for the tricky problems yet to come!

Use the starter kit to make your first submission.

💾 Dataset

The given dataset contains images of F1 cars. The images are of size 256*256 in jpg format. The bounding boxes are in bboxes with the columns as ImageId and bboxes containing list in [xmin, xmax, ymin, ymax] format.

A sample row :

The boxes will be in the string but to convert them into a python list, you can simply use literal_eval function from ast python library

📁 Files

Following files are available in the resources section:

• train.zip - (20000 samples) This zip file contains F1 images, with images name corresponding to ImageID column of train.csv
• train.csv - (20000 samples) This csv file contains the ImageID column corresponding to train.zip and bboxes the column contains bounding boxes in a list.
• val.zip - (2000 samples) This zip file contains F1 images, with images name corresponding to ImageID column of val.csv
• val.csv - (2000 samples) This csv file contains the ImageID column corresponding to val.zip and bboxes the column contains bounding boxes in a list.
• test.zip - (5000 samples) This zip file contains F1 images which will be used to evaluate the performance of the model.

🚀 Submission

• Prepare a CSV containing ImageID column corresponding to test.zip and bboxes column as bounding boxes. 

• ImageID	bboxes
  0	[[34, 65, 69, 98, 0.98]]
  1	[[36, 63, 98, 2, 0.5]]

• 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 the evaluation, Average Precision 

(AR) @[ IoU=0.50:0.50 | area=all | maxDets=1 ] 

will be used to test the efficiency of the model

🔗 Links

• 💪 Challenge Page: https://www.aicrowd.com/challenges/f1-car-detection
• 🗣️ Discussion Forum: https://www.aicrowd.com/challenges/f1-car-detection/discussion
• 🏆 Leaderboard: https://www.aicrowd.com/challenges/f1-car-detection/leaderboards

📱 Contact

• Shubhamai