MNIST 

Using layer_dense


```{r}
network <- keras_model_sequential() |> 
  layer_dense(units = 512, activation = "relu") |> 
  layer_dense(units = 10, activation = "softmax")
```

```{r}
network |> compile(
  optimizer = "rmsprop",
  loss = "categorical_crossentropy",
  metrics = c("accuracy")
)
```

Using layer_cov_2d and layer_max_pooling


```{r}
library(keras3)

inputs <- keras_input(shape = c(28, 28, 1))
outputs <- inputs |>
  layer_conv_2d(filters = 64, kernel_size = 3, activation = "relu") |>
  layer_max_pooling_2d(pool_size = 2) |>
  layer_conv_2d(filters = 128, kernel_size = 3, activation = "relu") |>
  layer_max_pooling_2d(pool_size = 2) |>
  layer_conv_2d(filters = 256, kernel_size = 3, activation = "relu") |>
  layer_global_average_pooling_2d() |>
  layer_dense(10, activation = "softmax")

model_no_max_pool <- keras_model(inputs = inputs, outputs = outputs)
```

```{r}
model |> compile(
  optimizer = "rmsprop",
  loss = "categorical_crossentropy",
  metrics = c("accuracy")
)
```

```{r}
model |> fit(
  train_images, train_labels,
  epochs = 5, batch_size=64
)
```

```{r}
model |> evaluate(test_images, test_labels)
```

Dogs vs Cats

```{r}
inputs <- keras_input(shape = c(180, 180, 3))                                   # <1>
outputs <- inputs |>
  layer_rescaling(1 / 255) |>                                                   # <2>
  layer_conv_2d(filters = 32, kernel_size = 3, activation = "relu") |>
  layer_max_pooling_2d(pool_size = 2) |>
  layer_conv_2d(filters = 64, kernel_size = 3, activation = "relu") |>
  layer_max_pooling_2d(pool_size = 2) |>
  layer_conv_2d(filters = 128, kernel_size = 3, activation = "relu") |>
  layer_max_pooling_2d(pool_size = 2) |>
  layer_conv_2d(filters = 256, kernel_size = 3, activation = "relu") |>
  layer_max_pooling_2d(pool_size = 2) |>
  layer_conv_2d(filters = 512, kernel_size = 3, activation = "relu") |>
  layer_global_average_pooling_2d() |>                                          # <3>
  layer_dense(1, activation = "sigmoid")

model <- keras_model(inputs, outputs)
```