Round 1: Completed #educational Weight: 30.0
4396
242
14
167

## 🕵️ Introduction

An F1 racing grid is chaotic! When cars are driven at high speed, it often leaves a bit of a mess around them. Be it in the form of burn tire bits, sparks from the car body or smoke from the exhaust! Racers often call the smoke coming from behind a car “dirty air” which makes navigating tricky and reduces their speed. Can you help them out by removing the smoke from images of cars and provide clarity?

In this problem, you’ll be provided with an image, your job is to remove the smoke from this image using your AI model and output a clean image. Here’s a starter code kit to help you out!

## 💾 Dataset

The given dataset contains images of F1 cars with smoke as the noise. You need to remove the smoke and make the F1 car visible. Each image is in RGB format with size of [256,256] and are in .jpg format.

## 📁 Files

Following files are available in the resources section:

• train.zip - (20000 samples) This zip contains the training dataset containing smoke and clear images.

• val.zip - (2000 samples) This zip contains a validation dataset containing smoke and clear Images.

• test.zip - (5000 samples) This zip will be used for actual evaluation for the leaderboard

## 🚀 Submission

• Prepare a zip containing clear folder containing predicted images with the name matching the corresponding folder names of test.zip
• The name of the above file should be submission.zip.
• Sample submission format available at sample_submission.zip in the resources section.

Make your first submission here 🚀 !!

## 🖊 Evaluation Criteria

During the evaluation, the average Mean Squared Error will be calculated over all the testing images.

np.mean((real_img - predicted_img)**2)

is the code for calculating MSE for images.

## 📱 Contact

#### Notebooks

 3 Smoke Elimination using FFA-Net Model MSE: 12.538 By g_mothy Almost 2 years ago 0 0 [Baseline] F1 Smoke Elimination By Shubhamaicrowd Almost 2 years ago 0