A tutorial for MNIST handwritten digit classification using sklearn, PyTorch and Keras.
numpy_matplotlib_sklearn.ipynb
: for numpy, matplotlib and sklearn.pytorch.ipynb
: for pytorch.keras.ipynb
: for keras.- Reference solution: (not published yet)
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
Please read HEAR.
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 |