TensorFlow-CPU安装和演示

TensorFlow-CPU安装和演示

TensorFlow可以用CPU作为计算单元，也可以用GPU作为计算单元。
TensorFlow-CPU就是用CPU作为计算单元的开源机器学习平台。
下面是在X86 CPU + Ubuntu上的安装和演示过程（在飞腾CPU平台上，我们后续再进行研究）。

在ubuntu上安装TensorFlow-CPU

简单三步，直接获取进行安装（在飞腾CPU平台验证，）
sudo apt-get update
sudo apt-get install python3-pip python3-dev
sudo pip3 install tensorflow-cpu

运行演示

建立演示test.py程序文件

import tensorflow as tf
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

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, activation='softmax')
        ])

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

model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test, verbose=2)

运行演示

python3 test.py

演示成功截图

2021-03-03 06:11:14.889341: I tensorflow/core/platform/profile_utils/cpu_utils.cc:112] CPU Frequency: 2400120000 Hz
Epoch 1/5
1875/1875 [==============================] - 4s 2ms/step - loss: 0.4827 - accuracy: 0.8585
Epoch 2/5
1875/1875 [==============================] - 4s 2ms/step - loss: 0.1479 - accuracy: 0.9548
Epoch 3/5
1875/1875 [==============================] - 4s 2ms/step - loss: 0.1067 - accuracy: 0.9684
Epoch 4/5
1875/1875 [==============================] - 4s 2ms/step - loss: 0.0907 - accuracy: 0.9727
Epoch 5/5
1875/1875 [==============================] - 3s 2ms/step - loss: 0.0757 - accuracy: 0.9768
313/313 - 1s - loss: 0.0705 - accuracy: 0.9787