---
title: "MNIST - CNN"
author: "Dr. Hua Zhou"
date: "3/15/2018"
output: 
  html_document:
    toc: true
    toc_depth: 4
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
sessionInfo()
```

Source: <https://tensorflow.rstudio.com/keras/articles/examples/mnist_cnn.html>

In this example, we train a convolutional neural networks (CNN) on the [MNIST](https://en.wikipedia.org/wiki/MNIST_database) data set. Achieve testing accuracy 99.16% after 12 epochs.

- The **MNIST** database (Modified National Institute of Standards and Technology database) is a large database of handwritten digits ($28 \times 28$) that is commonly used for training and testing machine learning algorithms.

- 60,000 training images, 10,000 testing images. 

## Prepare data

For CNN, instead of vectorizing the images, we keep the 2D structure.
```{r}
library(keras)

# Data Preparation -----------------------------------------------------

batch_size <- 128
num_classes <- 10
epochs <- 12

# Input image dimensions
img_rows <- 28
img_cols <- 28

# The data, shuffled and split between train and test sets
mnist <- dataset_mnist()
x_train <- mnist$train$x
y_train <- mnist$train$y
x_test <- mnist$test$x
y_test <- mnist$test$y

# Redefine  dimension of train/test inputs
x_train <- array_reshape(x_train, c(nrow(x_train), img_rows, img_cols, 1))
x_test <- array_reshape(x_test, c(nrow(x_test), img_rows, img_cols, 1))
input_shape <- c(img_rows, img_cols, 1)

# Transform RGB values into [0,1] range
x_train <- x_train / 255
x_test <- x_test / 255

cat('x_train_shape:', dim(x_train), '\n')
cat(nrow(x_train), 'train samples\n')
cat(nrow(x_test), 'test samples\n')

# Convert class vectors to binary class matrices
y_train <- to_categorical(y_train, num_classes)
y_test <- to_categorical(y_test, num_classes)
```

## Define model

Define model:
```{r}
model <- keras_model_sequential()
model %>%
  layer_conv_2d(filters = 32, kernel_size = c(3,3), activation = 'relu',
                input_shape = input_shape) %>% 
  layer_conv_2d(filters = 64, kernel_size = c(3,3), activation = 'relu') %>% 
  layer_max_pooling_2d(pool_size = c(2, 2)) %>% 
  layer_dropout(rate = 0.25) %>% 
  layer_flatten() %>% 
  layer_dense(units = 128, activation = 'relu') %>% 
  layer_dropout(rate = 0.5) %>% 
  layer_dense(units = num_classes, activation = 'softmax')
```
Compile model:
```{r}
# Compile model
model %>% compile(
  loss = loss_categorical_crossentropy,
  optimizer = optimizer_adadelta(),
  metrics = c('accuracy')
)
summary(model)
```

## Train and evaluate

```{r}
system.time({
history <- model %>% fit(
  x_train, y_train,
  batch_size = batch_size,
  epochs = epochs,
  verbose = 1,
  validation_data = list(x_test, y_test)
)
})
plot(history)
```

Testing:
```{r}
scores <- model %>% evaluate(
  x_test, y_test, verbose = 0
)

# Output metrics
cat('Test loss:', scores[[1]], '\n')
cat('Test accuracy:', scores[[2]], '\n')
```