TensorFlow 2 quickstart for experts

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

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

2025-12-01 07:58:53.594395: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
E0000 00:00:1764575933.617066  335130 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
E0000 00:00:1764575933.624660  335130 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
W0000 00:00:1764575933.642798  335130 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1764575933.642818  335130 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1764575933.642820  335130 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
W0000 00:00:1764575933.642822  335130 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.
TensorFlow version: 2.19.1

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)

I0000 00:00:1764575938.765668  335130 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 13638 MB memory:  -> device: 0, name: Tesla T4, pci bus id: 0000:00:05.0, compute capability: 7.5
I0000 00:00:1764575938.768025  335130 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:1 with 13756 MB memory:  -> device: 1, name: Tesla T4, pci bus id: 0000:00:06.0, compute capability: 7.5
I0000 00:00:1764575938.770313  335130 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:2 with 13756 MB memory:  -> device: 2, name: Tesla T4, pci bus id: 0000:00:07.0, compute capability: 7.5
I0000 00:00:1764575938.772495  335130 gpu_device.cc:2019] Created device /job:localhost/replica:0/task:0/device:GPU:3 with 13756 MB memory:  -> device: 3, name: Tesla T4, pci bus id: 0000:00:08.0, compute capability: 7.5

class MyModel(Model):
  def __init__(self):
    super().__init__()
    self.conv1 = Conv2D(32, 3, activation='relu')
    self.flatten = Flatten()
    self.d1 = Dense(128, activation='relu')
    self.d2 = Dense(10)

  def call(self, x):
    x = self.conv1(x)
    x = self.flatten(x)
    x = self.d1(x)
    return self.d2(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 = 5

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

  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():0.2f}, '
    f'Accuracy: {train_accuracy.result() * 100:0.2f}, '
    f'Test Loss: {test_loss.result():0.2f}, '
    f'Test Accuracy: {test_accuracy.result() * 100:0.2f}'
  )

I0000 00:00:1764575941.678208  335298 cuda_dnn.cc:529] Loaded cuDNN version 91600
Epoch 1, Loss: 0.13, Accuracy: 96.07, Test Loss: 0.06, Test Accuracy: 98.00
Epoch 2, Loss: 0.04, Accuracy: 98.71, Test Loss: 0.06, Test Accuracy: 98.21
Epoch 3, Loss: 0.02, Accuracy: 99.39, Test Loss: 0.05, Test Accuracy: 98.36
Epoch 4, Loss: 0.01, Accuracy: 99.63, Test Loss: 0.05, Test Accuracy: 98.45
Epoch 5, Loss: 0.01, Accuracy: 99.72, Test Loss: 0.07, Test Accuracy: 98.08