翻譯自：https://tensorflow.google.cn/tutorials/quickstart/beginner

這是一個的使用Keras做如下事情的簡短介紹：

建立圖像分類的一個神經網絡。

訓練這個神經網絡。

最后，評估模型的精確度

下載和安裝TensorFlow 2。在你的應用程序中導入TensorFlow：

from __future__ import absolute_import, division, print_function, unicode_literals import tensorflow as tf

載入并準備好MNIST數據集，將樣本由整數轉化為浮點數：

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

將模型的各層堆疊起來，以搭建tf.keras.Sequential模型。為訓練選擇優化器和損失函數。

model = tf.keras.models.Sequential([tf.keras.layers.Flatten(input_shape=(28, 28)),tf.keras.layers.Dense(128, activation='relu'),tf.keras.layers.Dropout(0.2),tf.keras.layers.Dense(10) ])

為每個例子模型返回一個向量的"logits"和”log-odds”分數，一個案例如下：

predictions = model(x_train[:1]).numpy() print(predictions)

輸出結果如下：

[[ 0.3304124 0.21085967 -0.26375788 0.18900187 -0.38255388 -0.42568913-0.5831184 0.68005246 0.11979596 0.22090217]]

tf.nn.softmax函數將logits轉化為每個類的概率。

tf.nn.softmax(predictions).numpy() print(tf.nn.softmax(predictions).numpy())

輸出結果如下：

[[0.08072349 0.15725857 0.10213858 0.08166214 0.12849897 0.119416420.09160781 0.10133947 0.05636909 0.08098544]]

The losses.SparseCategoricalCrossentropy loss takes a vector of logits and a True index and returns a scalar loss for each example.

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

這個損失等于真實類的負對數概率，如果模型確定這個類是正確的，那么它是零。

這個未經訓練的模型給出了接近隨機的概率(每個類的1/10)，因此這個最原初的loss可能接近于-tf.log(1/10) ~= 2.3。

loss_fn(y_train[:1], predictions).numpy()

輸出結果：

3.2944663 model.compile(optimizer='adam',loss=loss_fn,metrics=['accuracy'])

The Model.fit method adjusts the model parameters to minimize the loss:

model.fit(x_train,y_train,epochs=5)

輸出結果：

Epoch 1/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.2981 - accuracy: 0.9123 Epoch 2/5 1875/1875 [==============================] - 3s 2ms/step - loss: 0.1431 - accuracy: 0.9582 Epoch 3/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.1062 - accuracy: 0.9679 Epoch 4/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.0860 - accuracy: 0.9735 Epoch 5/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.0731 - accuracy: 0.9776

Model.evaluate方法檢查這個模型的性能，通過是在”驗證集”或”測試集”上。

model.evaluate(x_test,y_test,verbose=2)

輸出結果：

[0.0841476172208786, 0.9760000109672546]

在這個數據集上，這個圖片分類的模型訓練的準確率約等于98%。如果想了解更多關于這方面的內容，可以閱讀 TensorFlow tutorials.（https://tensorflow.google.cn/tutorials/）

如果你想你的模型返回一個概率，你可以包裹你的model對象，并且附帶softmax。如下：

probability_model = tf.keras.Sequential([model,tf.keras.layers.Softmax() ])print(probability_model(x_test[:5]))

輸出結果：

tf.Tensor( [[6.64528272e-08 7.67723236e-08 7.54364783e-06 3.53052717e-046.87170390e-11 3.60848901e-07 2.23684981e-12 9.99635696e-011.65168018e-07 3.13543705e-06][4.35788428e-09 1.10600071e-04 9.99865294e-01 8.18846547e-067.86288894e-14 1.47804167e-06 2.56378456e-07 2.10501798e-121.42125145e-05 1.13504149e-16][4.76928733e-07 9.98138189e-01 6.59115176e-05 5.00368878e-051.88655074e-04 4.11117344e-06 2.92819695e-05 9.81064513e-045.41346439e-04 7.17659077e-07][9.99821723e-01 2.42099341e-10 8.32889509e-06 8.88995942e-074.28884217e-09 8.21065169e-06 1.50513850e-04 8.60030013e-065.22520800e-08 1.76794254e-06][7.08432890e-06 4.52548754e-09 8.52964968e-06 8.69868177e-099.96985734e-01 3.78219802e-08 3.12174535e-07 1.97316593e-042.47502101e-07 2.80086603e-03]], shape=(5, 10), dtype=float32)

整體的代碼是：

# -*- coding: UTF-8 -*-from __future__ import absolute_import, division, print_function, unicode_literals import tensorflow as tffrom tensorflow.keras.layers import Dense, Flatten, Conv2D from tensorflow.keras import Modelmnist = 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]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)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()loss_object = tf.keras.losses.SparseCategoricalCrossentropy() optimizer = tf.keras.optimizers.Adam()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')@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)@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epoch開始是，重置評估指標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：

[[-0.28416255 0.22787774 0.1536147 0.1858716 0.06911337 0.829228940.21581247 0.5613003 0.44787267 -0.02493771]] [[0.0566914 0.09460051 0.0878297 0.09070901 0.0807129 0.172606420.09346598 0.13203742 0.11787888 0.07346781]] 1.7567413 Epoch 1/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.2980 - accuracy: 0.9137 Epoch 2/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.1436 - accuracy: 0.9563 Epoch 3/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.1051 - accuracy: 0.9681 Epoch 4/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.0875 - accuracy: 0.9730 Epoch 5/5 1875/1875 [==============================] - 3s 1ms/step - loss: 0.0754 - accuracy: 0.9762 313/313 - 0s - loss: 0.0728 - accuracy: 0.9784 [0.07283254712820053, 0.9783999919891357] tf.Tensor( [[6.64528272e-08 7.67723236e-08 7.54364783e-06 3.53052717e-046.87170390e-11 3.60848901e-07 2.23684981e-12 9.99635696e-011.65168018e-07 3.13543705e-06][4.35788428e-09 1.10600071e-04 9.99865294e-01 8.18846547e-067.86288894e-14 1.47804167e-06 2.56378456e-07 2.10501798e-121.42125145e-05 1.13504149e-16][4.76928733e-07 9.98138189e-01 6.59115176e-05 5.00368878e-051.88655074e-04 4.11117344e-06 2.92819695e-05 9.81064513e-045.41346439e-04 7.17659077e-07][9.99821723e-01 2.42099341e-10 8.32889509e-06 8.88995942e-074.28884217e-09 8.21065169e-06 1.50513850e-04 8.60030013e-065.22520800e-08 1.76794254e-06][7.08432890e-06 4.52548754e-09 8.52964968e-06 8.69868177e-099.96985734e-01 3.78219802e-08 3.12174535e-07 1.97316593e-042.47502101e-07 2.80086603e-03]], shape=(5, 10), dtype=float32)

總結

以上是生活随笔為你收集整理的04_面向初学者的快速入门、建立图像分类的一个神经网络、训练这个神经网络、评估模型的精确度的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。