🛠 Contribute: Found a typo? Or any other change in the description that you would like to see? Please consider sending us a pull request in the public repo of the challenge here.
🕵️ Introduction
Our writers were tired of introducing problems to you, well we decided to give them a break! Voila, the one problem which needs no introduction! life started by learning numbers, well you've come a full circle! let's get back to it !
We give you the very famous MNIST dataset of handwritten digits, can you identify them?
Understand with code! Here is getting started code for you.😄
💾 Dataset
The MNIST database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits that is commonly used for training various image processing systems.The database is also widely used for training and testing in the field of machine learning.Each image is 28
pixels in height and 28
pixels in width, for a total of 784
pixels in total. Each pixel has a single pixel-value associated with it, indicating the lightness or darkness of that pixel, with higher numbers meaning darker. This pixel-value is an integer between 0
and 255
, inclusive.
For simplification, images has been stored in csv file. The train.csv
has 785
columns, the fist column is the label and the rest 784
contain the pixel value of the associated image pixel.
📁 Files
Following files are available in the resources
section:
train.csv
- (60000
samples) This csv file contains the pixel values as columns along with the digits it represent.test.csv
- (10000
samples) File that will be used for actual evaluation for the leaderboard score and it does not have the digit represented by the pixel values.
🚀 Submission
- Prepare a csv containing header as
label
and predicted value as digit[0-9]
with name assubmission.csv
. - Sample submission format available at
sample_submission.csv
.
🚀 Submission
- Prepare a CSV containing header as
label
and predicted value as digit[0=9]
respectively denoting the digits - Name of the above file should be
submission.csv
. - Sample submission format available at
sample_submission.csv
in the resorces section.
Make your first submission here 🚀 !!
🖊 Evaluation Criteria
During evaluation F1 score will be used to test the efficiency of the model where,
🔗 Links
- 💪 Challenge Page : https://www.aicrowd.com/challenges/mnist
- 🗣️ Discussion Forum : https://www.aicrowd.com/challenges/mnist/discussion
- 🏆 leaderboard : https://www.aicrowd.com/challenges/mnist/leaderboard