챕터 7장

Mix.install([
  {:axon, "~> 0.5"},
  {:nx, "~> 0.5"},
  {:exla, "~> 0.5"},
  {:stb_image, "~> 0.6"},
  {:kino, "~> 0.8"}
])

Nx.global_default_backend(EXLA.Backend)

Section

defmodule CatsAndDogs do
  def pipeline(paths, batch_size, target_height, target_width) do
    paths
    |> Enum.shuffle()
    |> Task.async_stream(&parse_image/1)
    |> Stream.filter(fn
      {:ok, {%StbImage{}, _}} -> true
        _ -> false  
    end)
    |> Stream.map(&to_tensor(&1, target_height, target_width))
    |> Stream.chunk_every(batch_size, batch_size, :discard)
    |> Stream.map(fn chunks ->
      {img_chunk, label_chunk} = Enum.unzip(chunks)
      {Nx.stack(img_chunk), Nx.stack(label_chunk)}
    end)
  end

  def pipeline_with_argumentations(
    paths,
    batch_size,
    target_height,
    target_width
  ) do
    paths
    |> Enum.shuffle()
    |> Task.async_stream(&parse_image/1)
    |> Stream.filter(fn
      {:ok, {%StbImage{}, _}} -> true
      _ -> false
    end)
    |> Stream.map(&to_tensor(&1, target_height, target_width))
    |> Stream.map(&random_flip(&1, :height))
    |> Stream.map(&random_flip(&1, :width))
    |> Stream.chunk_every(batch_size, batch_size, :discard)
    |> Stream.map(fn chunks ->
      {img_chunk, label_chunk} = Enum.unzip(chunks)
      {Nx.stack(img_chunk), Nx.stack(label_chunk)}
    end)
  end

  defp parse_image(path) do
    label = if String.contains?(path, "cat"), do: 0, else: 1

    case StbImage.read_file(path) do
      {:ok, img} -> {img, label}
      _error -> :error
    end
  end

  defp to_tensor({:ok, {img, label}}, target_height, target_width) do
    img_tensor =
      img
      |> StbImage.resize(target_height, target_width)
      |> StbImage.to_nx()
      |> Nx.divide(255)
    label_tensor = Nx.tensor([label])

    {img_tensor, label_tensor}
  end

  defp random_flip({image, label}, axis) do
    if :rand.uniform() < 0.5 do
      {Nx.reverse(image, axes: [axis]), label}
    else
      {image, label}
    end
  end
end

{test_paths, train_paths} =
  Path.wildcard("train/*.jpg")
  |> Enum.shuffle()
  |> Enum.split(1000)

batch_size = 128
target_height = 96
target_width = 96

train_pipeline = CatsAndDogs.pipeline_with_argumentations(
  train_paths, batch_size, target_height, target_width
)

test_pipline = CatsAndDogs.pipeline(
  test_paths, batch_size, target_height, target_width
)

Enum.take(train_pipeline, 1)

mlp_model =
  Axon.input("images", shape: {nil, target_height, target_width, 3})
  |> Axon.flatten()
  |> Axon.dense(256, activation: :relu)
  |> Axon.dense(128, activation: :relu)
  |> Axon.dense(1, activation: :sigmoid)

mlp_trained_model_state =
  mlp_model
  |> Axon.Loop.trainer(:binary_cross_entropy, :adam)
  |> Axon.Loop.metric(:accuracy)
  |> Axon.Loop.run(train_pipeline, %{}, epochs: 5, compiler: EXLA)

mlp_model
|> Axon.Loop.evaluator()
|> Axon.Loop.metric(:accuracy)
|> Axon.Loop.run(test_pipline, mlp_trained_model_state, compiler: EXLA)

path = "train/dog.5.jpg"

img =
  path
  |> StbImage.read_file!()
  |> StbImage.to_nx()
  |> Nx.transpose(axes: [:channels, :height, :width])
  |> Nx.new_axis(0)

kernel = Nx.tensor([
  [-1, 0, 1],
  [-1, 0, 1],
  [-1, 0, 1],
])
kernel = kernel |> Nx.reshape({1, 1, 3, 3}) |> Nx.broadcast({3, 3, 3, 3})

img
|> Nx.conv(kernel)
|> Nx.as_type({:u, 8})
|> Nx.squeeze(axes: [0])
|> Nx.transpose(axes: [:height, :width, :channels])
|> Kino.Image.new()

cnn_model = Axon.input("images", shape: {nil, 96, 96, 3})

template = Nx.template({1, 96, 96, 3}, :f32)

Axon.Display.as_graph(cnn_model, template)

cnn_model =
  Axon.input("images", shape: {nil, 96, 96, 3})
  |> Axon.conv(32, kernel_size: {3, 3}, activation: :relu, padding: :same)
  |> Axon.max_pool(kernel_size: {2, 2}, strides: [2, 2])
  |> Axon.conv(64, kernel_size: {3, 3}, activation: :relu, padding: :same)
  |> Axon.max_pool(kernel_size: {2, 2}, strides: [2, 2])
  |> Axon.conv(128, kernel_size: {3, 3}, activation: :relu, padding: :same)
  |> Axon.max_pool(kernel_size: {2, 2}, strides: [2, 2])
  |> Axon.flatten()
  |> Axon.dense(128, activation: :relu)
  |> Axon.dense(1, activation: :sigmoid)
  

Axon.Display.as_graph(cnn_model, template)

cnn_trained_model_state =
cnn_model
|> Axon.Loop.trainer(:binary_cross_entropy, :adam)
|> Axon.Loop.metric(:accuracy)
|> Axon.Loop.run(train_pipeline, %{}, epochs: 5, compiler: EXLA)

cnn_model
|> Axon.Loop.evaluator()
|> Axon.Loop.metric(:accuracy)
|> Axon.Loop.run(test_pipline, cnn_trained_model_state, compiler: EXLA)

cnn_model =
Axon.input("images", shape: {nil, 96, 96, 3})
|> Axon.conv(32, kernel_size: {3, 3}, activation: :relu, padding: :same) |> Axon.max_pool(kernel_size: {2, 2}, strides: [2, 2])
|> Axon.conv(64, kernel_size: {3, 3}, activation: :relu, padding: :same) |> Axon.max_pool(kernel_size: {2, 2}, strides: [2, 2])
|> Axon.conv(128, kernel_size: {3, 3}, activation: :relu, padding: :same) |> Axon.max_pool(kernel_size: {2, 2}, strides: [2, 2])
|> Axon.flatten()
|> Axon.dense(128, activation: :relu)
|> Axon.dense(1, activation: :sigmoid)

cnn_trained_model_state =
cnn_model
|> Axon.Loop.trainer(:binary_cross_entropy, :adam)
|> Axon.Loop.metric(:accuracy)
|> Axon.Loop.run(train_pipeline, %{}, epochs: 5, compiler: EXLA)

cnn_model
|> Axon.Loop.evaluator()
|> Axon.Loop.metric(:accuracy)
|> Axon.Loop.run(test_pipeline, cnn_trained_model_state, compiler: EXLA)

{test_paths, train_paths} =
  Path.wildcard("train/*.jpg")
  |> Enum.shuffle()
  |> Enum.split(1000)

batch_size = 128
target_height = 96
target_width = 96

train_pipeline = CatsAndDogs.pipeline_with_argumentations(
  train_paths, batch_size, target_height, target_width
)

test_pipline = CatsAndDogs.pipeline(
  test_paths, batch_size, target_height, target_width
)

Enum.take(train_pipeline, 1)