cantabile-kwok / mnist_tutorial

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

mnist_tutorial

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

Code structure

• numpy_matplotlib_sklearn.ipynb: for numpy, matplotlib and sklearn.
• pytorch.ipynb: for pytorch.
• keras.ipynb: for keras.
• Reference solution: (not published yet)
  • numpy_matplotlib_sklearn_solution.ipynb
  • pytorch_solution.ipynb
  • keras_solution.ipynb

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.

Results (519030910352 郭奕玮)

使用了PyTorch框架（1.7.1）， sklearn版本为0.24.0

问题	Training Accuracy （%）	Test Accuracy （%）
Q1	97.63	87.00
Q2	81.95	80.00
Q3	97.90	86.00
Q4	91.40	89.90
Q5	99.61	99.17