Skip to content

PavelKrinitsin/Digit-Recognizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

Digit Recognizer

Educational task on building a classifier for handwritten digit images based on the MNIST dataset

Description

Цель данной работы - построение классификатора изображений рукописного ввода на базе библиотеки MNIST. Классификатор построен на признаках, полученных в результате предобработки изображений. Работа выполнена в рамках выполнения задания на https://www.kaggle.com/c/digit-recognizer. В качестве модели классификатора выбрана модель KNN. Подбор гиперпараметров осуществлен с помощью GridSearch.

The aim of this work is to build a classifier for handwritten digit images based on the MNIST library. The classifier is built on features obtained from image preprocessing. The work was done as part of a task on https://www.kaggle.com/c/digit-recognizer. The KNN model was chosen as the classifier model. Hyperparameter tuning was done using GridSearch.


Results

Метрика оцененана тестовой выборке в рамках контеста Digit Recognizer на Kaggle. Accuracy: 0,620.

The metric was evaluated on the test set within the Digit Recognizer contest on Kaggle. Accuracy: 0.620.


Tags

Python, Machine Learning, Classification tasks

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published