/mnist_tutorial

A tutorial for MNIST handwritten digit classification using sklearn, PyTorch and Keras.

Primary LanguageJupyter Notebook

My Solution

Environment

  • Windows 10
  • Python 3.8.5(64-bit,Anaconda)
  • matplotlib 3.3.2
  • scikit-learn 0.23.2
  • pytorch 1.7.1
  • numpy 1.19.1

Solution

Pytorch is used.CUDA version: 11.1.

Question Train Acc. (%) Test Acc. (%)
Q1 97.22% 87.90%
Q2 82.00% 81.50%
Q3 97.97% 85.20%
Q4 92.25% 88.40%
Q5 97.61% 97.88%

mnist_tutorial

A tutorial for mnist hand writen digit classification using sklearn, pytorch and keras. A tutorial for MNIST handwritten digit classification using sklearn, PyTorch and Keras.

Code structure

Requirements

Code tested on following environments, other version should also work:

  • linux system (ubuntu 16.04)
  • python 3.6.3
  • numpy 1.13.3
  • matplotlib 2.1.0
  • sklearn 0.19.1
  • pytorch 0.4.1
  • keras 2.1.2

For students from SJTU

Please read HEAR.