import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' # 设置日志级别为ERROR，以减少警告信息
# 禁用 Gemini 的底层库（gRPC 和 Abseil）在初始化日志警告
os.environ["GRPC_VERBOSITY"] = "ERROR"
os.environ["GLOG_minloglevel"] = "3" # 0: INFO, 1: WARNING, 2: ERROR, 3: FATAL
os.environ["GLOG_minloglevel"] = "true"
import logging
import tensorflow as tf
tf.get_logger().setLevel(logging.ERROR)
tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)
!export TF_FORCE_GPU_ALLOW_GROWTH=true
专家的 TensorFlow 2 快速入门#
 View on TensorFlow.org
|
 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。Python 程序可以直接在浏览器中运行，这是学习和使用 Tensorflow 的绝佳方式。要按照本教程操作，请点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：在菜单栏的右上方，选择 CONNECT。
运行所有笔记本代码单元：选择 Runtime > Run all。
下载并安装 TensorFlow 2。将 TensorFlow 导入您的程序：
注：升级 pip 以安装 TensorFlow 2 软件包。请参阅安装指南了解详细信息。
将 TensorFlow 导入到您的程序：
import tensorflow as tf
print("TensorFlow version:", tf.__version__)
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
TensorFlow version: 2.17.0
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 将数据集分批和重排：
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()
选择用于训练的优化器和损失函数：
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。这些指标在周期内累积值，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_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}'
)
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
Cell In[10], line 5
1 EPOCHS = 5
3 for epoch in range(EPOCHS):
4 # Reset the metrics at the start of the next epoch
----> 5 train_loss.reset_states()
6 train_accuracy.reset_states()
7 test_loss.reset_states()
AttributeError: 'Mean' object has no attribute 'reset_states'
现在，经过训练，照片分类器在此数据集上的准确率约为 98%。要了解详情，请阅读 TensorFlow 教程。