48   Deep Learning

简单的神经网络:全链接

 

 

download
代码解释:

def main(_):
  # Import data
  # 加载训练数据和测试数据
  mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)

  # Create the model
  # 定义图像输入变量 x , 作为训练和测试数据的入口,None 表示可输入任意数量的图片,每张图片有 784 个像素,即 784 个 x 变量
  x = tf.placeholder(tf.float32, [None, 784])
  # 定义变量 x 的参数 w,因为后面会追加偏移量 b,同时输出是 10 个结果集(1到10的可能性概率)
  W = tf.Variable(tf.zeros([784, 10]))
  b = tf.Variable(tf.zeros([10]))
  # 简单的全网络链接,通过矩阵计算输出结果集合
  y = tf.matmul(x, W) + b

  # Define loss and optimizer
  y_ = tf.placeholder(tf.float32, [None, 10])

  # The raw formulation of cross-entropy,
  #
  #   tf.reduce_mean(-tf.reduce_sum(y_ * tf.log(tf.nn.softmax(y)),
  #                                 reduction_indices=[1]))
  #
  # can be numerically unstable.
  #
  # So here we use tf.nn.softmax_cross_entropy_with_logits on the raw
  # outputs of 'y', and then average across the batch.
  # 计算模型输出结果和真实结果的误差,采用交叉熵作为损失函数
  cross_entropy = tf.reduce_mean(
      tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))
  # 训练步伐,通过求导计算,一点点地逼近损失函数的极值点
  train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

  # 初始化流程图
  sess = tf.InteractiveSession()
  tf.global_variables_initializer().run()
  # Train
  # 开始训练,一共训练 1000 次,每次读取 100 张图片,避免一次性读入太多图片导致内存不足或者计算量过大的问题
  for _ in range(1000):
    batch_xs, batch_ys = mnist.train.next_batch(100)
    sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})

  # Test trained model
  # 测试模型的准确率
  correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
  accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
  print(sess.run(accuracy, feed_dict={x: mnist.test.images,
                                      y_: mnist.test.labels}))



Leave a Reply

Your email address will not be published. Required fields are marked *