https://tensorflow.google.cn/tutorials/quickstart/advanced

導(dǎo)入TensorFlow到你的程序中：

import tensorflow as tf from tensorflow.keras.layers import Dense, Flatten, Conv2D from tensorflow.keras import Model

加載和準(zhǔn)備MNIST數(shù)據(jù)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]

使用 tf.data 來(lái)將數(shù)據(jù)集切分為 batch 以及混淆數(shù)據(jù)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 模型子類化（model subclassing） API構(gòu)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, activation='softmax')def call(self, x):x = self.conv1(x)x = self.flatten(x)x = self.d1(x)return self.d2(x)model = MyModel()

為訓(xùn)練選擇優(yōu)化器與損失函數(shù)：

loss_object = tf.keras.losses.SparseCategoricalCrossentropy() optimizer = tf.keras.optimizers.Adam()

選擇衡量指標(biāo)來(lái)度量模型的損失值（loss）和準(zhǔn)確率（accuracy）。這些指標(biāo)在epoch上累積值，然后打印出整理結(jié)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來(lái)訓(xùn)練模型：

@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)

測(cè)試模型：

@tf.function def test_step(images, labels):predictions = model(images)t_loss = loss_object(labels, predictions)test_loss(t_loss)test_accuracy(labels, predictions)EPOCHS = 5 for epoch in range(EPOCHS):# 在下一個(gè)epoch開(kāi)始是，重置評(píng)估指標(biāo)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)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))

輸出結(jié)果：

WARNING:tensorflow:Layer my_model is casting an input tensor from dtype float64 to the layer's dtype of float32, which is new behavior in TensorFlow 2. The layer has dtype float32 because it's dtype defaults to floatx. If you intended to run this layer in float32, you can safely ignore this warning. If in doubt, this warning is likely only an issue if you are porting a TensorFlow 1.X model to TensorFlow 2. To change all layers to have dtype float64 by default, call `tf.keras.backend.set_floatx('float64')`. To change just this layer, pass dtype='float64' to the layer constructor. If you are the author of this layer, you can disable autocasting by passing autocast=False to the base Layer constructor. Epoch 1, Loss: 0.13633669912815094, Accuracy: 95.92000579833984, Test Loss: 0.054682306945323944, Test Accuracy: 98.19999694824219 Epoch 2, Loss: 0.041911669075489044, Accuracy: 98.70333099365234, Test Loss: 0.04665009677410126, Test Accuracy: 98.4000015258789 Epoch 3, Loss: 0.021748166531324387, Accuracy: 99.31666564941406, Test Loss: 0.05017175152897835, Test Accuracy: 98.36000061035156 Epoch 4, Loss: 0.01320651639252901, Accuracy: 99.55166625976562, Test Loss: 0.058168746531009674, Test Accuracy: 98.30999755859375 Epoch 5, Loss: 0.008145572617650032, Accuracy: 99.7316665649414, Test Loss: 0.06632857024669647, Test Accuracy: 98.30999755859375 與50位技術(shù)專家面對(duì)面20年技術(shù)見(jiàn)證，附贈(zèng)技術(shù)全景圖

總結(jié)

以上是生活随笔為你收集整理的05_专家的快速入门、加载MNIST数据集、数据集切分和混淆、定义类的方式构建模型、选择优化器和损失函数、训练模型和测试模型准确率的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問(wèn)題。

如果覺(jué)得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。