#! /usr/bin/env python3
#
def dogs_vs_cats ( ):

#*****************************************************************************80
#
## dogs_vs_cats() classifies images of dogs and cats.
#
#  Discussion:
#
#    The data consists of jpeg images of dogs and cats.
#
#  Licensing:
#
#    This code is distributed under the MIT license.
#
#  Modified:
#
#    08 January 2025
#
#  Author:
#
#    Original keras version by Francois Chollet;
#    This version by John Burkardt.
#
#  Reference:
#
#    Francois Chollet,
#    Deep Learning with Python,
#    Second Edition,
#    Manning, 2021,
#    ISBN: 9781617296864.
#
  import matplotlib.pyplot as plt
  import numpy as np
  import platform
  import tensorflow

  from tensorflow import keras
  from tensorflow.keras import layers

  print ( '' )
  print ( 'dogs_vs_cats():' )
  print ( '  python version:     ' + platform.python_version ( ) )
  print ( '  numpy version:      ' + np.version.version )
  print ( '  tensorflow version: ' + tensorflow.__version__ )
  print ( '' )
  print ( '  Use a convolutional neural model' )
  print ( '  to classify jpeg images of dogs and cats.' )
#
#  Build the model.
#
  inputs = keras.Input ( shape = ( 180, 180, 3 ) )
  x = layers.Rescaling ( 1.0 / 255 ) ( inputs )
  x = layers.Conv2D ( filters = 32, kernel_size = 3, activation = 'relu' )(x)
  x = layers.MaxPooling2D ( pool_size = 2 ) ( x )
  x = layers.Conv2D ( filters = 64, kernel_size = 3, activation = 'relu' )(x)
  x = layers.MaxPooling2D ( pool_size = 2 ) ( x )
  x = layers.Conv2D ( filters = 128, kernel_size = 3, activation = 'relu' )(x)
  x = layers.MaxPooling2D ( pool_size = 2 ) ( x )
  x = layers.Conv2D ( filters = 256, kernel_size = 3, activation = 'relu' )(x)
  x = layers.MaxPooling2D ( pool_size = 2 ) ( x )
  x = layers.Conv2D ( filters = 256, kernel_size = 3, activation = 'relu' )(x)
  x = layers.Flatten() ( x )

  outputs = layers.Dense ( 1, activation = 'sigmoid' ) ( x )
  model = keras.Model ( inputs = inputs, outputs = outputs )
#
#  Look at how the dimensions of the feature maps change with each
#  successive level.
#
  model.summary ( )
#
#  Configure the model for training.
#
  model.compile ( \
    loss = 'binary_crossentropy', \
    optimizer = 'rmsprop', \
    metrics = [ 'accuracy' ] )
#
#  Read the images.
#
  from tensorflow.keras.utils import image_dataset_from_directory

  new_base_dir ='/home/john/public_html/keras_src/dogs_vs_cats_data'
  train_dataset = image_dataset_from_directory (
    '/home/john/public_html/keras_src/dogs_vs_cats_data/train',
    image_size = ( 180, 180 ),
    batch_size = 32 )

  validation_dataset = image_dataset_from_directory (
    '/home/john/public_html/keras_src/dogs_vs_cats_data/validation',
    image_size = ( 180, 180 ),
    batch_size = 32 )

  test_dataset = image_dataset_from_directory (
    '/home/john/public_html/keras_src/dogs_vs_cats_data/test',
    image_size = ( 180, 180 ),
    batch_size = 32 )
#
#  Look at the shape of data (32,180,180,3) and labels (32,) in a single batch.
#
  for data_batch, labels_batch in train_dataset:
    print ( 'data_batch.shape:  ', data_batch.shape )
    print ( 'labels_batch.shape:', labels_batch.shape )
    break
#
#  Fit the model using a dataset.
#
  callbacks = [
    keras.callbacks.ModelCheckpoint (
      filepath = 'convnet_from_scratch.keras',
      save_best_only = True,
      monitor = 'val_loss' )
  ]

  history = model.fit ( \
    train_dataset, \
    steps_per_epoch = 100, \
    epochs = 10, \
    validation_data = validation_dataset, \
    callbacks = callbacks )
#
#  Display loss and accuracy during training.
#

  accuracy = history.history[ 'accuracy' ]
  val_accuracy = history.history[ 'val_accuracy' ]
  loss = history.history[ 'loss' ]
  val_loss = history.history[ 'val_loss' ]

  epochs = range ( 1, len ( accuracy ) + 1 )

  plt.plot ( epochs, accuracy, 'bo', label = 'Training accuracy' )
  plt.plot ( epochs, val_accuracy, 'b', label = 'Validation accuracy' )
  plt.title ( 'Training and validation accuracy' )
  plt.grid ( True )
  plt.legend ( )
  filename = 'dogs_vs_cats1_tvacc.png'
  plt.savefig ( filename )
  print ( '' )
  print ( '  Graphics saved as "' + filename + '"' )
  plt.show ( )

  plt.plot ( epochs, loss, 'ro', label = 'Training loss' )
  plt.plot ( epochs, val_loss, 'r', label = 'Validation loss' )
  plt.title ( 'Training and validation loss' )
  plt.grid ( True )
  plt.legend ( )
  filename = 'dogs_vs_cats1_tvloss.png'
  plt.savefig ( filename )
  print ( '' )
  print ( '  Graphics saved as "' + filename + '"' )
  plt.show ( )
#
#  Evaluate the model on the test set.
#
  test_model = keras.models.load_model ( 'convnet_from_scratch.keras' )
  test_loss, test_acc = test_model.evaluate ( test_dataset )
  print ( '  Test accuracy: ', test_acc )
#
#  Terminate.
#
  print ( '' )
  print ( 'dogs_vs_cats():' )
  print ( '  Normal end of execution.' )
  return

def timestamp ( ):

#*****************************************************************************80
#
## timestamp() prints the date as a timestamp.
#
#  Licensing:
#
#    This code is distributed under the MIT license. 
#
#  Modified:
#
#    06 April 2013
#
#  Author:
#
#    John Burkardt
#
  import time

  t = time.time ( )
  print ( time.ctime ( t ) )

  return None

if ( __name__ == '__main__' ):
  timestamp ( )
  dogs_vs_cats ( )
  timestamp ( )