My Homework Solution

Env

Code tested on following environments.

• Windows 10(20H2)
• Python 3.8.8(64-bit,Miniconda)
• matplotlib 3.3.4
• scikit-learn 0.24.1
• pytorch 1.6.0
• numpy 1.19.2

Solution

Pytorch is used. No CUDA.

Question	Train Acc. (%)	Test Acc. (%)
Q1	97.25%	87.90%
Q2	81.82%	81.00%
Q3	97.53%	85.90%
Q4	96.92%	86.50%
Q5	98.27%	98.39%

---

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.