针对专业人员的 TensorFlow 2.0 入门

使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。

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(notebook)文件。Python 程序直接在浏览器中运行——这是一种学习和使用 Tensorflow 的好方法。要学习本教程,请单击本页顶部按钮,在 Google Colab 中运行笔记本(notebook).

  1. 在 Colab 中,连接到 Python 运行时:在菜单栏右上角,选择连接(CONNECT)
  2. 运行所有笔记本(notebook)代码单元格:选择运行时(Runtime) > 运行所有(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
2022-08-31 06:27:39.569608: E tensorflow/stream_executor/cuda/cuda_blas.cc:2981] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2022-08-31 06:27:40.284198: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvrtc.so.11.1: cannot open shared object file: No such file or directory
2022-08-31 06:27:40.284463: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvrtc.so.11.1: cannot open shared object file: No such file or directory
2022-08-31 06:27:40.284476: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.
TensorFlow version: 2.10.0-rc3

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 来将数据集切分为 batch 以及混淆数据集:

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(MyModel, self).__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()

为训练选择优化器与损失函数:

loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

optimizer = tf.keras.optimizers.Adam()

选择衡量指标来度量模型的损失值(loss)和准确率(accuracy)。这些指标在 epoch 上累积值,然后打印出整体结果。

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 来训练模型:

@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}'
  )
Epoch 1, Loss: 0.14128023386001587, Accuracy: 95.79332733154297, Test Loss: 0.06780562549829483, Test Accuracy: 97.82999420166016
Epoch 2, Loss: 0.04480328410863876, Accuracy: 98.66667175292969, Test Loss: 0.053502410650253296, Test Accuracy: 98.36000061035156
Epoch 3, Loss: 0.023289579898118973, Accuracy: 99.26000213623047, Test Loss: 0.06082199141383171, Test Accuracy: 98.1500015258789
Epoch 4, Loss: 0.013719179667532444, Accuracy: 99.57167053222656, Test Loss: 0.058127060532569885, Test Accuracy: 98.44999694824219
Epoch 5, Loss: 0.010663792490959167, Accuracy: 99.61500549316406, Test Loss: 0.05961000174283981, Test Accuracy: 98.3499984741211

该图片分类器现在在此数据集上训练得到了接近 98% 的准确率(accuracy)。要了解更多信息,请阅读 TensorFlow 教程