安装命令:
1pip install tensorflow-gpu==2.0.0-alpha0
要开始,请将TensorFlow库导入您的程序:
xxxxxxxxxx
21from __future__ import absolute_import, division, print_function, unicode_literals
2import tensorflow as tf
加载并准备MNIST数据集,将样本从整数转换为浮点数:
x1mnist = tf.keras.datasets.mnist
2
3(x_train, y_train), (x_test, y_test) = mnist.load_data()
4x_train, x_test = x_train / 255.0, x_test / 255.0
通过堆叠图层构建tf.keras.Sequential
模型。选择用于训练的优化器和损失函数:
xxxxxxxxxx
101model = tf.keras.models.Sequential([
2 tf.keras.layers.Flatten(input_shape=(28, 28)),
3 tf.keras.layers.Dense(128, activation='relu'),
4 tf.keras.layers.Dropout(0.2),
5 tf.keras.layers.Dense(10, activation='softmax')
6])
7
8model.compile(optimizer='adam',
9 loss='sparse_categorical_crossentropy',
10 metrics=['accuracy'])
训练和评估模型:
xxxxxxxxxx
31model.fit(x_train, y_train, epochs=5)
2
3model.evaluate(x_test, y_test)
现在,图像分类器在该数据集上的准确度达到约98%。 要了解更多信息,请阅读TensorFlow教程.。
最新版本:https://www.mashangxue123.com/tensorflow/tf2-tutorials-quickstart-beginner.html 英文版本:https://tensorflow.google.cn/beta/tutorials/quickstart/beginner 翻译建议PR:https://github.com/mashangxue/tensorflow2-zh/edit/master/r2/tutorials/quickstart/beginner.md