TensorFlow快速入门深度学习框架

一个很有趣的个人博客,不信你来撩 fangzengye.com

TensorFlow源地址

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

一个简单的深度学习训练框架

导入TensorFlow包和在线加载数据集

mport 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

初始化神经网络层

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')
])

初始化模型参数（损失函数）

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

开始训练

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