AFAgarap

# It only has two dependencies numpy and tensorflow
import numpy as np
import tensorflow as tf

from config import cfg


# Class defining a Convolutional Capsule
# consisting of multiple neuron layers
#

AFAgarap

AFAgarap

AFAgarap

AFAgarap

"""TensorFlow 2.0 implementation of vanilla Autoencoder."""
import numpy as np
import tensorflow as tf

__author__ = "Abien Fred Agarap"

np.random.seed(1)
tf.random.set_seed(1)
batch_size = 128
epochs = 10

AFAgarap

class Encoder(tf.keras.layers.Layer):
  def __init__(self, intermediate_dim):
    super(Encoder, self).__init__()
    self.hidden_layer = tf.keras.layers.Dense(
      units=intermediate_dim,
      activation=tf.nn.relu,
      kernel_initializer='he_uniform'
    )
    self.output_layer = tf.keras.layers.Dense(
      units=intermediate_dim,

AFAgarap

class Decoder(tf.keras.layers.Layer):
  def __init__(self, intermediate_dim, original_dim):
    super(Decoder, self).__init__()
    self.hidden_layer = tf.keras.layers.Dense(
      units=intermediate_dim,
      activation=tf.nn.relu,
      kernel_initializer='he_uniform'
    )
    self.output_layer = tf.keras.layers.Dense(
      units=original_dim,

AFAgarap

class Autoencoder(tf.keras.Model):
  def __init__(self, intermediate_dim, original_dim):
    super(Autoencoder, self).__init__()
    self.encoder = Encoder(intermediate_dim=intermediate_dim)
    self.decoder = Decoder(intermediate_dim=intermediate_dim, original_dim=original_dim)
  
  def call(self, input_features):
    code = self.encoder(input_features)
    reconstructed = self.decoder(code)
    return reconstructed

AFAgarap

def loss(model, original):
  reconstruction_error = tf.reduce_mean(tf.square(tf.subtract(model(original), original)))
  return reconstruction_error

AFAgarap

def train(loss, model, opt, original):
  with tf.GradientTape() as tape:
    gradients = tape.gradient(loss(model, original), model.trainable_variables)
    gradient_variables = zip(gradients, model.trainable_variables)
    opt.apply_gradients(gradient_variables)