imgseg.py

import tensorflow as tf
from tensorflow.keras.layers.experimental import preprocessing 
import tensorflow_datasets as tfds
from tensorflow_examples.models.pix2pix import pix2pix

dataset, info = tfds.load('oxford_iiit_pet:3.*.*', with_info=True)

def normalize(input_image, input_mask):
  input_image = tf.cast(input_image, tf.float32) / 255.0
  input_mask -= 1
  return input_image, input_mask

def load_image(datapoint):
  input_image = tf.image.resize(datapoint['image'], (128, 128))
  input_mask = tf.image.resize(datapoint['segmentation_mask'], (128, 128))

  input_image, input_mask = normalize(input_image, input_mask)

  return input_image, input_mask

TRAIN_LENGTH = info.splits['train'].num_examples
BATCH_SIZE = 64
BUFFER_SIZE = 1000
STEPS_PER_EPOCH = TRAIN_LENGTH // BATCH_SIZE

train_images = dataset['train'].map(load_image, num_parallel_calls=tf.data.AUTOTUNE)
test_images = dataset['test'].map(load_image, num_parallel_calls=tf.data.AUTOTUNE)

class Augment(tf.keras.layers.Layer):
  def __init__(self, seed=42):
    super().__init__()
    # both use the same seed, so they'll make the same random changes.
    self.augment_inputs = preprocessing.RandomFlip(mode="horizontal", seed=seed)
    self.augment_labels = preprocessing.RandomFlip(mode="horizontal", seed=seed)
  
  def call(self, inputs, labels):
    inputs = self.augment_inputs(inputs)
    labels = self.augment_labels(labels)
    return inputs, labels

train_batches = (
    train_images
    .cache()
    .shuffle(BUFFER_SIZE)
    .batch(BATCH_SIZE)
    .repeat()
    .map(Augment())
    .prefetch(buffer_size=tf.data.AUTOTUNE))

test_batches = test_images.batch(BATCH_SIZE)
base_model = tf.keras.applications.MobileNetV2(input_shape=[128, 128, 3], include_top=False)

# Use the activations of these layers
layer_names = [
    'block_1_expand_relu',   # 64x64
    'block_3_expand_relu',   # 32x32
    'block_6_expand_relu',   # 16x16
    'block_13_expand_relu',  # 8x8
    'block_16_project',      # 4x4
]
base_model_outputs = [base_model.get_layer(name).output for name in layer_names]

# Create the feature extraction model
down_stack = tf.keras.Model(inputs=base_model.input, outputs=base_model_outputs)

down_stack.trainable = False

up_stack = [
    pix2pix.upsample(512, 3),  # 4x4 -> 8x8
    pix2pix.upsample(256, 3),  # 8x8 -> 16x16
    pix2pix.upsample(128, 3),  # 16x16 -> 32x32
    pix2pix.upsample(64, 3),   # 32x32 -> 64x64
]

def unet_model(output_channels:int):
  inputs = tf.keras.layers.Input(shape=[128, 128, 3])

  # Downsampling through the model
  skips = down_stack(inputs)
  x = skips[-1]
  skips = reversed(skips[:-1])

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

  # This is the last layer of the model
  last = tf.keras.layers.Conv2DTranspose(
      filters=output_channels, kernel_size=3, strides=2,
      padding='same')  #64x64 -> 128x128

  x = last(x)

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

OUTPUT_CLASSES = 3

model = unet_model(output_channels=OUTPUT_CLASSES)
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

EPOCHS = 20
VAL_SUBSPLITS = 5
VALIDATION_STEPS = info.splits['test'].num_examples//BATCH_SIZE//VAL_SUBSPLITS

model_history = model.fit(train_batches, epochs=EPOCHS,
                          steps_per_epoch=STEPS_PER_EPOCH,
                          validation_steps=VALIDATION_STEPS,
                          validation_data=test_batches)