import tensorflow as tf
print("TensorFlow version:", tf.__version__)

from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model



mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

# Add a channels dimension
x_train = x_train[..., tf.newaxis].astype("float32")
x_test = x_test[..., tf.newaxis].astype("float32")



train_ds = tf.data.Dataset.from_tensor_slices(
    (x_train, y_train)).shuffle(10000).batch(32)

test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)





class UAF(Model):
  def __init__(self):
    super(UAF, self).__init__()
    self.A = tf.Variable(10.0, trainable=True)  
    self.B = tf.Variable(0.0000012, trainable=True)   
    self.C = tf.Variable(0.0000001, trainable=True)  
    self.D = tf.Variable(9.0, trainable=True) 
    self.E = tf.Variable(0.00000102, trainable=True)   
    

  def call(self, input):
    P1 = (self.A*(input+self.B)) + (self.C *  tf.math.square(input))
    P2 = (self.D*(input-self.B))

    P3 =  tf.nn.relu(P1) + tf.math.log1p(tf.math.exp(-tf.math.abs(P1)))
    P4 =  tf.nn.relu(P2) + tf.math.log1p(tf.math.exp(-tf.math.abs(P2)))
    
    return P3 - P4  + self.E



class MyModel(Model):
  def __init__(self):
    super(MyModel, self).__init__()
    self.conv1 = Conv2D(32, 3, activation=None)
    self.flatten = Flatten()
    self.d1 = Dense(128, activation=None)
    self.d2 = Dense(10, activation=None)
    self.act0 = UAF()
    self.act1 = UAF()
    self.act2 = UAF()
    

  def call(self, x):
    x = self.conv1(x)
    x = self.act0(x)
    x = self.flatten(x)
    x = self.d1(x)
    x = self.act1(x)
    x = self.d2(x)
    return self.act2(x)

# Create an instance of the model
model = MyModel()





loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

optimizer = tf.keras.optimizers.Adam()



train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')

test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')




@tf.function
def train_step(images, labels):
  with tf.GradientTape() as tape:
    # training=True is only needed if there are layers with different
    # behavior during training versus inference (e.g. Dropout).
    predictions = model(images, training=True)
    loss = loss_object(labels, predictions)
  gradients = tape.gradient(loss, model.trainable_variables)
  optimizer.apply_gradients(zip(gradients, model.trainable_variables))

  train_loss(loss)
  train_accuracy(labels, predictions)


@tf.function
def test_step(images, labels):
  # training=False is only needed if there are layers with different
  # behavior during training versus inference (e.g. Dropout).
  predictions = model(images, training=False)
  t_loss = loss_object(labels, predictions)

  test_loss(t_loss)
  test_accuracy(labels, predictions)


EPOCHS = 20

for epoch in range(EPOCHS):
  # Reset the metrics at the start of the next epoch
  train_loss.reset_states()
  train_accuracy.reset_states()
  test_loss.reset_states()
  test_accuracy.reset_states()

  for images, labels in train_ds:
    train_step(images, labels)

  for test_images, test_labels in test_ds:
    test_step(test_images, test_labels)

  print(
    f'Epoch {epoch + 1}, '
    f'Loss: {train_loss.result()}, '
    f'Accuracy: {train_accuracy.result() * 100}, '
    f'Test Loss: {test_loss.result()}, '
    f'Test Accuracy: {test_accuracy.result() * 100}'
  )