在 TensorFlow.org 上查看
在 Google Colab 中运行
在 GitHub 上查看源代码
下载笔记本这是一个 Google Colaboratory 笔记本文件。Python 程序直接在浏览器中运行 - 这是学习和使用 TensorFlow 的好方法。要学习本教程，请通过单击此页面顶部的按钮在 Google Colab 中运行笔记本。
- 在 Colab 中，连接到 Python 运行时：在菜单栏的右上角，选择连接。
- 运行所有笔记本代码单元：选择运行时 > 运行全部。
下载并安装 TensorFlow 2。将 TensorFlow 导入您的程序
将 TensorFlow 导入您的程序
import tensorflow as tf
print("TensorFlow version:", tf.__version__)
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
2024-07-13 06:54:42.012604: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:479] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2024-07-13 06:54:42.038839: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:10575] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2024-07-13 06:54:42.038874: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1442] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered TensorFlow version: 2.16.2
加载并准备 MNIST 数据集。
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")
使用 tf.data 对数据集进行批处理和洗牌
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)
使用 Keras 模型子类化 API 构建 tf.keras 模型
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()
选择优化器和损失函数进行训练
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
optimizer = tf.keras.optimizers.Adam()
选择指标来衡量模型的损失和准确率。这些指标会累积每个 epoch 的值，然后打印总体结果。
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')
使用 tf.GradientTape 训练模型
@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)
测试模型
@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}'
)
2024-07-13 06:54:53.279724: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:54:53.895273: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 1, Loss: 0.13, Accuracy: 96.00, Test Loss: 0.06, Test Accuracy: 97.85 2024-07-13 06:54:58.213183: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:54:58.613194: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 2, Loss: 0.04, Accuracy: 98.70, Test Loss: 0.05, Test Accuracy: 98.36 2024-07-13 06:55:03.021925: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:55:03.409904: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 3, Loss: 0.02, Accuracy: 99.30, Test Loss: 0.06, Test Accuracy: 98.23 2024-07-13 06:55:07.799603: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence 2024-07-13 06:55:08.205513: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 4, Loss: 0.01, Accuracy: 99.55, Test Loss: 0.06, Test Accuracy: 98.14 2024-07-13 06:55:12.538723: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence Epoch 5, Loss: 0.01, Accuracy: 99.74, Test Loss: 0.07, Test Accuracy: 98.26 2024-07-13 06:55:12.943937: W tensorflow/core/framework/local_rendezvous.cc:404] Local rendezvous is aborting with status: OUT_OF_RANGE: End of sequence
该图像分类器现在在这个数据集上训练到了约 98% 的准确率。要了解更多信息，请阅读 TensorFlow 教程。