# MNIST Digit Model

Training data: `F:\ml\machine_learning_2026_spring\session-3\mnist_train.csv`

Test data: `F:\ml\machine_learning_2026_spring\session-3\mnist_test.csv`

Model: PyTorch small CNN

Test accuracy: `0.9860`

```text
              precision    recall  f1-score   support

           0       0.98      1.00      0.99       100
           1       0.98      1.00      0.99       100
           2       0.98      0.98      0.98       100
           3       0.99      0.99      0.99       100
           4       1.00      1.00      1.00       100
           5       0.98      0.99      0.99       100
           6       1.00      0.98      0.99       100
           7       0.96      0.97      0.97       100
           8       0.99      0.96      0.97       100
           9       1.00      0.99      0.99       100

    accuracy                           0.99      1000
   macro avg       0.99      0.99      0.99      1000
weighted avg       0.99      0.99      0.99      1000

```