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，樣本個數(shù)不確定為None
y = tf.placeholder(tf.float32, [None, n_classes]) # 用placeholder先占地方，樣本個數(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']) # 返回輸出層的結果，得到十個類別的得分值

pred = multilayer_perceptron(x, weights, biases) # 前向傳播的預測值
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y)) # 交叉熵損失函數(shù)，參數(shù)分別為預測值pred和實際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()對比預測值的索引和實際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,并對所有的判斷結果求均值
init = tf.global_variables_initializer()
print("FUNCTIONS READY")

# 上面神經(jīng)網(wǎng)絡結構定義好之后，下面定義一些超參數(shù)
training_epochs = 100 # 所有樣本迭代100次
batch_size = 100 # 每進行一次迭代選擇100個樣本
display_step = 5
# LAUNCH THE GRAPH
sess = tf.Session() # 定義一個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")