エキスパートのための TensorFlow 2 クイックスタート

コレクションでコンテンツを整理 必要に応じて、コンテンツの保存と分類を行います。

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

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

2024-01-11 21:56:03.385012: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-01-11 21:56:03.385056: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-01-11 21:56:03.386602: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
TensorFlow version: 2.15.0

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 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_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}'
  )

WARNING: All log messages before absl::InitializeLog() is called are written to STDERR
I0000 00:00:1705010170.188690  982259 device_compiler.h:186] Compiled cluster using XLA!  This line is logged at most once for the lifetime of the process.
Epoch 1, Loss: 0.14312978088855743, Accuracy: 95.6883316040039, Test Loss: 0.06150883808732033, Test Accuracy: 98.06999969482422
Epoch 2, Loss: 0.04425348341464996, Accuracy: 98.6199951171875, Test Loss: 0.05480688810348511, Test Accuracy: 98.18999481201172
Epoch 3, Loss: 0.023569559678435326, Accuracy: 99.23333740234375, Test Loss: 0.05095665156841278, Test Accuracy: 98.3699951171875
Epoch 4, Loss: 0.01400002371519804, Accuracy: 99.54833221435547, Test Loss: 0.05548116937279701, Test Accuracy: 98.43999481201172
Epoch 5, Loss: 0.010487733408808708, Accuracy: 99.62999725341797, Test Loss: 0.05794484168291092, Test Accuracy: 98.5