---
title: "MNIST Example Python"
author: "Prof. Eric A. Suess"
format: 
  html:
    embed-resources: true
---

## MNIST Feedforward neural network with **one** hidden layer

Load the packages

```{r}
library(tensorflow)
library(keras)
```

```{python}
import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt
```


Load the MNIST dataset.

```{python}
mnist = keras.datasets.mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
```


Examine the data.

```{python}
print(train_images.shape)
print(train_labels)
print(test_images.shape)
print(test_labels)

```

Preprocess the data.

```{python}
train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype('float32') / 255

test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255
```

Specify a neural network model.

```{python}
model = keras.Sequential([
    keras.layers.Dense(512, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])
```

```{python}
model.compile(optimizer='rmsprop',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])
```

Train the model.

```{python}
model.fit(train_images, train_labels, epochs=5, batch_size=128)
```

Evaluate the model.

```{python}
test_loss, test_acc = model.evaluate(test_images, test_labels)
print('Test accuracy:', test_acc)
```

Make predictions.

```{python}
predictions = model.predict(test_images)
print(predictions[0])
print(np.argmax(predictions[0]))
```