TF1.0_Multilayer-Perceptron_笔记

逐句

loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
    logits=logits, labels=Y))

• tf.nn.softmax_cross_entropy_with_logits(logits, labels, name=None)
  第一个参数logits：就是神经网络最后一层的输出，如果有batch的话，它的大小就是[batchsize，num_classes]，单样本的话，大小就是num_classes
  第二个参数labels：实际的标签，大小同上
• 参考: TensorFlow tf.nn.softmax_cross_entropy_with_logits的用法

batch_x, batch_y = mnist.train.next_batch(batch_size)

• mnist.train.next_batch是专门用于由tensorflow提供的MNIST教程的函数。它的工作原理是在开始时将训练图像和标签对随机化，并在每次调用该函数时选择每个随后的batch_size张图像。一旦到达末尾，图像标签对将再次随机分配，并重复该过程。仅在使用所有可用对后，才重新组合和重复整个数据集。

print("Epoch:", '%04d' % (epoch+1), "cost={:.9f}".format(avg_cost))

• %04d
  四位
  参考: Python–格式化输出%s和%d
• {:.9f}
  小数点后九位
  参考: Python中 {:.0f} 格式化输出

print("Accuracy:", accuracy.eval({X: mnist.test.images, Y: mnist.test.labels}))

• f.Tensor.eval(feed_dict=None, session=None)：
  作用：
  在一个Seesion里面“评估”tensor的值（其实就是计算），首先执行之前的所有必要的操作来产生这个计算这个tensor需要的输入，然后通过这些输入产生这个tensor。在激发tensor.eval()这个函数之前，tensor的图必须已经投入到session里面，或者一个默认的session是有效的，或者显式指定session.
  参数：
  feed_dict:一个字典，用来表示tensor被feed的值（联系placeholder一起看）
  session:（可选） 用来计算（evaluate）这个tensor的session.要是没有指定的话，那么就会使用默认的session。
  返回：
  表示“计算”结果值的numpy ndarray
  参考: TensorFlow中.eval()函数理解

过程

• 数据集加载处理，参数设置
• 图输入，图w,b设置
• 建立，构建模型multilayer_perceptron
• 定义损失函数和优化器，初始化
• session会话，训练，测试

代码

""" Multilayer Perceptron.

A Multilayer Perceptron (Neural Network) implementation example using
TensorFlow library. This example is using the MNIST database of handwritten
digits (http://yann.lecun.com/exdb/mnist/).

Links:
    [MNIST Dataset](http://yann.lecun.com/exdb/mnist/).

Author: Aymeric Damien
Project: https://github.com/aymericdamien/TensorFlow-Examples/
"""

# ------------------------------------------------------------------
#
# THIS EXAMPLE HAS BEEN RENAMED 'neural_network.py', FOR SIMPLICITY.
#
# ------------------------------------------------------------------


from __future__ import print_function

# Import MNIST data
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)

import tensorflow as tf

# Parameters
learning_rate = 0.001
training_epochs = 15
batch_size = 100
display_step = 1

# Network Parameters
n_hidden_1 = 256 # 1st layer number of neurons
n_hidden_2 = 256 # 2nd layer number of neurons
n_input = 784 # MNIST data input (img shape: 28*28)
n_classes = 10 # MNIST total classes (0-9 digits)

# tf Graph input
X = tf.placeholder("float", [None, n_input])
Y = tf.placeholder("float", [None, n_classes])

# Store layers weight & bias
weights = {
    'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1])),
    'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
 }
biases = {
    'b1': tf.Variable(tf.random_normal([n_hidden_1])),
    'b2': tf.Variable(tf.random_normal([n_hidden_2])),
    'out': tf.Variable(tf.random_normal([n_classes]))
}

# Create model
def multilayer_perceptron(x):
    # Hidden fully connected layer with 256 neurons
    layer_1 = tf.add(tf.matmul(x, weights['h1']), biases['b1'])
    # Hidden fully connected layer with 256 neurons
    layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
    # Output fully connected layer with a neuron for each class
    out_layer = tf.matmul(layer_2, weights['out']) + biases['out'])
    return out_layer

# Construct model
logits = multilayer_perceptron(X)

# Define loss and optimizer
loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(
    logits=logits, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss_op)
# Initializing the variables
init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)

    # Training cycle
    for epoch in range(training_epochs):
        avg_cost = 0.
        total_batch = int(mnist.train.num_examples/batch_size) #总数 / 一次 = 共多少次
        # Loop over all batches
        for i in range(total_batch):
            batch_x, batch_y = mnist.train.next_batch(batch_size)
            # Run optimization op (backprop) and cost op (to get loss value)
            _, c = sess.run([train_op, loss_op], feed_dict={X: batch_x,
                                                            Y: batch_y})
            # Compute average loss
            avg_cost += c / total_batch
        # Display logs per epoch step
        if epoch % display_step == 0:
            print("Epoch:", '%04d' % (epoch+1), "cost={:.9f}".format(avg_cost))
    print("Optimization Finished!")

    ##############################????????????for???????????????#############################
    # Test model
    pred = tf.nn.softmax(logits)  # Apply softmax to logits
    correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(Y, 1))
    # Calculate accuracy
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
    print("Accuracy:", accuracy.eval({X: mnist.test.images, Y: mnist.test.labels}))