首先需要安装tensorflow2.0版本,这个版本与1.x的版本变化比较大,主要采用了keras的API,具体可以参考
一、下面是以jupyter notebook开发环境为例进行代码演示,jupyter notebook需要在命令行签名增加!
!pip install tensorflow-gpu==2.0.0-alpha0
二、导入使用到的库
from __future__ import absolute_import, division, print_function, unicode_literals
import tensorflow as tf
from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
三、加载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]
x_test = x_test[..., tf.newaxis]
四、切分数据集(训练数据、测试数据)
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)
五、建立模型
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, activation='softmax')
def call(self, x):
x = self.conv1(x)
x = self.flatten(x)
x = self.d1(x)
return self.d2(x)
model = MyModel()
六、定义损失函数和优化器
loss_object = tf.keras.losses.SparseCategoricalCrossentropy()
optimizer = tf.keras.optimizers.Adam()
七、定义模型训练和测试的损失值和精确率
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')
八、使用GradientTape进行模型训练
@tf.function
def train_step(images, labels):
with tf.GradientTape() as tape:
predictions = model(images)
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)
九、定义测试模型的方法
@tf.function
def test_step(images, labels):
predictions = model(images)
t_loss = loss_object(labels, predictions)
test_loss(t_loss)
test_accuracy(labels, predictions)
十、开始训练,并且同时输出训练和测试的损失值和精确率
EPOCHS = 5
for epoch in range(EPOCHS):
for images, labels in train_ds:
train_step(images, labels)
for test_images, test_labels in test_ds:
test_step(test_images, test_labels)
template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
print (template.format(epoch+1,
train_loss.result(),
train_accuracy.result()*100,
test_loss.result(),
test_accuracy.result()*100))