mnist dataset with 99.40+ % validation accuracy

While i had an task of company,where they had mentioned an condition to get,

  1. Validation accuracy on mnist dataset upto 99.40%
  2. Total parameter must be less than 8000

i successfully done that,and get an 99.43% validation accuracy on mnist dataset after running model for around 1200 epoch…and its an big achievement for me….

i shared an my google colab notbook on Github …

The Link is:

Blog By:

Akshay Bhor: Deep learning Engineer

an Data Scientist




Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Create your own dashboard using PowerBI

Why My Cognitive Science Degree Was A Great Foundation For Data Science and Machine Learning

Yukon — Optimized File Deduplication and Merge

Billion-Scale Investigation of COVID-19 Impact on Human Communication in 104 Languages

5 things I learned by analysing Kaggle’s 2020 Machine Learning and Data Science Survey

Bluff your estimate in roughly 3.4 minutes

BERT Visualization in Embedding Projector

Measuring Content Engagement in the PR industry

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Akshay Bhor Data Scientist

Akshay Bhor Data Scientist

More from Medium

Visualization of deep neural networks

How to perform clustering with dimensionality reduction for large datasets

Human Pose Estimation

Before MTH 513, I had never studied or even looked that deep into machine learning or…