import tensorflow as tf
import numpy as np
import input_data
mnist = input_data.read_data_sets('data/', one_hot=True)
n_hidden_1 = 256
n_input = 784
n_classes  = 10
# INPUTS AND OUTPUTS
x = tf.placeholder(tf.float32, [None, n_input]) # 用placeholder先占地方，樣本個(gè)數(shù)不確定為None
y = tf.placeholder(tf.float32, [None, n_classes]) # 用placeholder先占地方，樣本個(gè)數(shù)不確定為None
# NETWORK PARAMETERS
weights = {
 'w1': tf.Variable(tf.random_normal([n_input, n_hidden_1], stddev=0.1)),
 'out': tf.Variable(tf.zeros([n_hidden_1, n_classes]))
}
biases = {
 'b1': tf.Variable(tf.zeros([n_hidden_1])),
 'out': tf.Variable(tf.zeros([n_classes]))
}
print("NETWORK READY")
def multilayer_perceptron(_X, _weights, _biases): # 前向傳播，l1、l2每一層后面加relu激活函數(shù)
 layer_1 = tf.nn.relu(tf.add(tf.matmul(_X, _weights['w1']), _biases['b1'])) # 隱層
 return (tf.matmul(layer_1, _weights['out']) + _biases['out']) # 返回輸出層的結(jié)果，得到十個(gè)類別的得分值
pred = multilayer_perceptron(x, weights, biases) # 前向傳播的預(yù)測(cè)值
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) # 交叉熵?fù)p失函數(shù)，參數(shù)分別為預(yù)測(cè)值pred和實(shí)際label值y，reduce_mean為求平均loss
optm = tf.train.GradientDescentOptimizer(0.01).minimize(cost) # 梯度下降優(yōu)化器
corr = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) # tf.equal()對(duì)比預(yù)測(cè)值的索引和實(shí)際label的索引是否一樣，一樣返回True，不一樣返回False
accr = tf.reduce_mean(tf.cast(corr, tf.float32)) # 將pred即True或False轉(zhuǎn)換為1或0,并對(duì)所有的判斷結(jié)果求均值
init = tf.global_variables_initializer()
print("FUNCTIONS READY")
# 上面神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)定義好之后，下面定義一些超參數(shù)
training_epochs = 100 # 所有樣本迭代100次
batch_size = 100 # 每進(jìn)行一次迭代選擇100個(gè)樣本
display_step = 5
# LAUNCH THE GRAPH
sess = tf.Session() # 定義一個(gè)Session
sess.run(init) # 在sess里run一下初始化操作
# OPTIMIZE
for epoch in range(training_epochs):
 avg_cost = 0.
 total_batch = int(mnist.train.num_examples/batch_size)
 # Loop over all batches
 for i in range(total_batch):
  batch_xs, batch_ys = mnist.train.next_batch(batch_size) # 逐個(gè)batch的去取數(shù)據(jù)
  sess.run(optm, feed_dict={x: batch_xs, y: batch_ys})
  avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys})/total_batch
 # Display logs per epoch step
 if epoch % display_step == 0:
  train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys})
  test_acc = sess.run(accr, feed_dict={x: mnist.test.images, y: mnist.test.labels})
  print("Epoch: %03d/%03d cost: %.9f TRAIN ACCURACY: %.3f TEST ACCURACY: %.3f"
  % (epoch, training_epochs, avg_cost, train_acc, test_acc))
print("DONE")