Pix2Pix

show more

Implementations

Pix2Pix implementation with Tensorflow 2.0 and Keras

Build the Generator

  • The architecture of generator is a modified U-Net
  • Each block in the encoder is (Conv -> Batchnorm -> Leaky ReLU)
  • Each block in the decoder is (Transposed Conv -> Batchnorm -> Dropout(applied to the first 3 blocks) -> ReLU)
  • There are skip connections between the encoder and decoder (as in U-Net)
def downsample(filters, size, apply_batchnorm=True):
  initializer = tf.random_normal_initializer(0., 0.02)

  result = tf.keras.Sequential()
  result.add(
      tf.keras.layers.Conv2D(filters, size, strides=2, padding='same',
                             kernel_initializer=initializer, use_bias=False))

  if apply_batchnorm:
    result.add(tf.keras.layers.BatchNormalization())

  result.add(tf.keras.layers.LeakyReLU())

  return result
down_model = downsample(3, 4)
down_result = down_model(tf.expand_dims(inp, 0))
print (down_result.shape)
(1, 128, 128, 3)
def upsample(filters, size, apply_dropout=False):
  initializer = tf.random_normal_initializer(0., 0.02)

  result = tf.keras.Sequential()
  result.add(
    tf.keras.layers.Conv2DTranspose(filters, size, strides=2,
                                    padding='same',
                                    kernel_initializer=initializer,
                                    use_bias=False))

  result.add(tf.keras.layers.BatchNormalization())

  if apply_dropout:
      result.add(tf.keras.layers.Dropout(0.5))

  result.add(tf.keras.layers.ReLU())

  return result
up_model = upsample(3, 4)
up_result = up_model(down_result)
print (up_result.shape)
(1, 256, 256, 3)
def Generator():
  down_stack = [
    downsample(64, 4, apply_batchnorm=False), # (bs, 128, 128, 64)
    downsample(128, 4), # (bs, 64, 64, 128)
    downsample(256, 4), # (bs, 32, 32, 256)
    downsample(512, 4), # (bs, 16, 16, 512)
    downsample(512, 4), # (bs, 8, 8, 512)
    downsample(512, 4), # (bs, 4, 4, 512)
    downsample(512, 4), # (bs, 2, 2, 512)
    downsample(512, 4), # (bs, 1, 1, 512)
  ]

  up_stack = [
    upsample(512, 4, apply_dropout=True), # (bs, 2, 2, 1024)
    upsample(512, 4, apply_dropout=True), # (bs, 4, 4, 1024)
    upsample(512, 4, apply_dropout=True), # (bs, 8, 8, 1024)
    upsample(512, 4), # (bs, 16, 16, 1024)
    upsample(256, 4), # (bs, 32, 32, 512)
    upsample(128, 4), # (bs, 64, 64, 256)
    upsample(64, 4), # (bs, 128, 128, 128)
  ]

  initializer = tf.random_normal_initializer(0., 0.02)
  last = tf.keras.layers.Conv2DTranspose(OUTPUT_CHANNELS, 4,
                                         strides=2,
                                         padding='same',
                                         kernel_initializer=initializer,
                                         activation='tanh') # (bs, 256, 256, 3)

  concat = tf.keras.layers.Concatenate()

  inputs = tf.keras.layers.Input(shape=[None,None,3])
  x = inputs

  # Downsampling through the model
  skips = []
  for down in down_stack:
    x = down(x)
    skips.append(x)

  skips = reversed(skips[:-1])

  # Upsampling and establishing the skip connections
  for up, skip in zip(up_stack, skips):
    x = up(x)
    x = concat([x, skip])

  x = last(x)

  return tf.keras.Model(inputs=inputs, outputs=x)

Build the Discriminator

  • The Discriminator is a PatchGAN
  • Each block in the discriminator is (Conv -> BatchNorm -> Leaky ReLU)
  • The shape of the output after the last layer is (batch_size, 30, 30, 1)
  • Each 30x30 patch of the output classifies a 70x70 portion of the input image (such an architecture is called a PatchGAN).
  • Discriminator receives 2 inputs.
    • Input image and the target image, which it should classify as real.
    • Input image and the generated image (output of generator), which it should classify as fake.
    • We concatenate these 2 inputs together in the code (tf.concat([inp, tar], axis=-1))
def Discriminator():
  initializer = tf.random_normal_initializer(0., 0.02)

  inp = tf.keras.layers.Input(shape=[None, None, 3], name='input_image')
  tar = tf.keras.layers.Input(shape=[None, None, 3], name='target_image')

  x = tf.keras.layers.concatenate([inp, tar]) # (bs, 256, 256, channels*2)

  down1 = downsample(64, 4, False)(x) # (bs, 128, 128, 64)
  down2 = downsample(128, 4)(down1) # (bs, 64, 64, 128)
  down3 = downsample(256, 4)(down2) # (bs, 32, 32, 256)

  zero_pad1 = tf.keras.layers.ZeroPadding2D()(down3) # (bs, 34, 34, 256)
  conv = tf.keras.layers.Conv2D(512, 4, strides=1,
                                kernel_initializer=initializer,
                                use_bias=False)(zero_pad1) # (bs, 31, 31, 512)

  batchnorm1 = tf.keras.layers.BatchNormalization()(conv)

  leaky_relu = tf.keras.layers.LeakyReLU()(batchnorm1)

  zero_pad2 = tf.keras.layers.ZeroPadding2D()(leaky_relu) # (bs, 33, 33, 512)

  last = tf.keras.layers.Conv2D(1, 4, strides=1,
                                kernel_initializer=initializer)(zero_pad2) # (bs, 30, 30, 1)

  return tf.keras.Model(inputs=[inp, tar], outputs=last)
discriminator = Discriminator()
disc_out = discriminator([inp[tf.newaxis,...], gen_output], training=False)

You can find more details in Tensorflow 2.0 implementations Here

@Tensorflow2.0

kerastensorflow2pix2pix
How helpful was this page?