 View on TensorFlow.org
|
 Run in Google Colab
|
 View source on GitHub
|
 Download notebook
|
This is a Google Colaboratory notebook file. Python programs are run directly in the browser—a great way to learn and use TensorFlow. To follow this tutorial, run the notebook in Google Colab by clicking the button at the top of this page.
- In Colab, connect to a Python runtime: At the top-right of the menu bar, select CONNECT.
- Run all the notebook code cells: Select Runtime > Run all.
Download and install TensorFlow 2. Import TensorFlow into your program:
Import TensorFlow into your program:
import tensorflow as tf
print("TensorFlow version:", tf.__version__)
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
2024-07-19 04:53:00.545325: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-07-19 04:53:00.566309: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-07-19 04:53:00.572682: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered TensorFlow version: 2.17.0
Load and prepare the MNIST dataset.
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")
Use tf.data to batch and shuffle the dataset:
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)
WARNING: All log messages before absl::InitializeLog() is called are written to STDERR I0000 00:00:1721364783.805920 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.809276 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.812852 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.816460 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.828100 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.831170 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.834449 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.837815 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.841401 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.844378 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.847739 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364783.851044 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.105451 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.107686 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.109706 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.111768 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.113813 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.115897 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.117824 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.119782 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.121736 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.123803 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.125708 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.127659 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.166394 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.168582 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.170567 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.172600 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.174573 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.176651 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.178580 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.180556 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.182507 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.185156 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.187518 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355 I0000 00:00:1721364785.189859 59296 cuda_executor.cc:1015] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero. See more at https://github.com/torvalds/linux/blob/v6.0/Documentation/ABI/testing/sysfs-bus-pci#L344-L355
Build the tf.keras model using the Keras model subclassing API:
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()
Choose an optimizer and loss function for training:
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
optimizer = tf.keras.optimizers.Adam()
Select metrics to measure the loss and the accuracy of the model. These metrics accumulate the values over epochs and then print the overall result.
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')
Use tf.GradientTape to train the model:
@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)
Test the model:
@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}'
)
W0000 00:00:1721364787.210582 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.251679 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.252867 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.254041 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.255193 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.263856 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.267000 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.270105 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.271317 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.272560 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.273751 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.276057 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.295402 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.296650 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.297872 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.299380 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.300612 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.441431 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.443842 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.445166 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.449549 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.451025 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.453189 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.454861 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.457537 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.460401 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.463998 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364787.478406 59459 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.498664 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.499407 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.500060 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.500713 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.501368 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.502039 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.502697 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.503348 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.504001 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.504663 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.505337 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.505984 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.506633 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.507280 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.507958 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.508606 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.509258 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced W0000 00:00:1721364792.509966 59462 gpu_timer.cc:114] Skipping the delay kernel, measurement accuracy will be reduced Epoch 1, Loss: 0.14, Accuracy: 95.88, Test Loss: 0.06, Test Accuracy: 98.09 Epoch 2, Loss: 0.04, Accuracy: 98.66, Test Loss: 0.06, Test Accuracy: 98.04 Epoch 3, Loss: 0.02, Accuracy: 99.22, Test Loss: 0.06, Test Accuracy: 98.18 Epoch 4, Loss: 0.01, Accuracy: 99.57, Test Loss: 0.06, Test Accuracy: 98.35 Epoch 5, Loss: 0.01, Accuracy: 99.67, Test Loss: 0.07, Test Accuracy: 98.34
The image classifier is now trained to ~98% accuracy on this dataset. To learn more, read the TensorFlow tutorials.