Skip to content

Implementations of various classifiers on MNIST dataset. Both traditional machine learning and deep learning methods are included.

Notifications You must be signed in to change notification settings

shishishu/mnist-classification-tutorial

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MNIST-CLASSIFICATION-TUTORIAL

Overview

  • Algorithms
    • Machine learning: LR, SVM, XGBoost, MLP
    • Deep learning: CNN, ResNet, VAE, Distilling Knowledge, Data-Free Learning
  • Framework
    • Sklearn
    • Tensorflow
    • Pytorch

Progress

Model Framework Main Params Test Accuracy Time Cost /s Comments
LR sklearn solver='liblinear', multi_class='ovr' 0.9202 57.87
SVM sklearn kernel='rbf', decision_function_shape='ovr' 0.9446 556.91
XGBoost sklearn max_depth=5, n_jobs=10 0.9651 141.38
MLP sklearn hidden_layer_sizes=(128, 32) 0.9768 44.80
MLP tensorflow batch_size=512, learning_rate=1e-3, hidden_layers=[128,32] 0.9795 39.05
CNN tensorflow batch_size=256, learning_rate=1e-5, num_epoch=100 0.9785 1062.03
ResNet
VAE
Distilling Knowledge
Data-Free Learning

Reference

About

Implementations of various classifiers on MNIST dataset. Both traditional machine learning and deep learning methods are included.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages