AI Blitz X: Completed #educational Weight: 10.0
3336
262
15
215

Welcome to AI Blitz X! 🚀

Community Explainer Prizes 📓  |  Find Teammates 👯‍♀️

Easy-2-Follow Notebooks 💻   | Discord AI Community 🎧

# Introduction

As a throwback to Blitz 7, we are putting on our spacesuit again!

Docking is the process of joining one spacecraft to another space station. It is a very high-precision task, requiring accurate hand-eye coordination. Even a small mistake can lead to failure.

SpaceX Dragon spacecraft attempted autonomous docking but what if the sensors onboard malfunctioned?! Can you dock a spacecraft successfully using only the input from the camera?

Your first Blitz X task is to calculate the distance and the central location of the docking port given the input image.

You can start solving the problem using our starter kit! If you are curious about docking, check out this real-life example!

## 💪 Getting Started

In this challenge, the task is to calculate the distance between the Spacecraft & ISS. and the central location of the docking port.

Use our Getting Started Notebook available here.

## 💾 Dataset

In the train set. There are 2 files train.zip & train.csv. Sample train.csv

 ImageID distance location 0 293 [224, 272] 1 464 [236, 364] 2 92 [269, 339]

• The ImageID column In train.csv is corresponding to the image name in the train.zip.
• The distance column represents the distance from the picture to the docking port on ISS.
• The location is the pixel coordinates ( x, y ) of the docking port.

Few things to note -

• The camera angle does not affect the distance from ISS Docking Port.
• The point of reference for calculating the distance is always the same.
• The camera is stationary in generating the samples.

## 📁 Files

Following files are available in the resources section:

• train.zip - (10000 samples) -  File containing images for the training set.

• train.csv - (10000 samples) -  File containing labels for the training set.

• val.zip - (1000 samples) -  File containing images for the validation set.

• val.csv - (1000 samples) -  File containing labels for the validation set.

• test.zip - (5000 samples) - File containing images for the testing set.

• submission.csv - (5000 samples) - File containing sample labels for the testing set.

## 🚀  Submission

• Creating a submission directory
• Use submission.csv and fill the corresponding labels.
• Save the submission.csv in the assets directory. The name of the above file should be submission.csv.
• Inside a submission directory, put the .ipynb notebook from which you trained the model and made inference and save it as original_notebook.ipynb.
• Overall, this is what your submission directory should look like -
submission
├── assets
│   └── submission.csv
└── original_notebook.ipynb
• Zip the submission directory!

Make your first submission here 🚀 !!

## 🖊 Evaluation Criteria

During the evaluation. For the Distance & Location Column, Mean Squared Error will be used to test the efficiency of the model.