tf.nn.conv2d(x,kernel,strides=[1,1,1,1],padding='SAME')
# kernel[0,1]数表示卷积核的尺寸，
# kernel[2]表示channel数量，灰度图片是1，RGB图是3
# kernel[3]表示卷积核的数量
# padding='SAME'表示边界加上padding，使得卷积的输入和输出保持同样的尺寸。所加的padding为0，也就是边界补0
# padding='VALID'表示取样不超过边框，也就是 no padding

tf.nn.max_pool(x,ksize=[1,3,3,1],strides=[1,2,2,1],padding='SAME')
# 池化尺寸3*3，横竖步长为2*2
# padding='SAME'表示加边框,使池化层的输出输出保持同样的尺寸
# padding='VALID'表示取样不超过边框，

tf.contrib.layers.flatten(inputs, outputs_collections=None, scope=None)
# inputs: A tensor of size [batch_size, ...]
# outputs_collections: Collection to add the outputs.
# scope: Optional scope for name_scope.
# Returns: A flattened tensor with shape [batch_size, k].

tf.contrib.layers.fully_connected(
    inputs,
    num_outputs,
    activation_fn=tf.nn.relu,
    weights_initializer=initializers.xavier_initializer(),
    weights_regularizer=None,
    biases_initializer=tf.zeros_initializer(),
    biases_regularizer=None,
    trainable=True,
    scope=None
)
# inputs: [batch_size, depth], [None, None, None, channels].
# activation_fn: Activation function. The default value is a ReLU function.
# scope: Optional scope for variable_scope.

import requests
url = 'https://github.com/guofei9987/datasets_for_ml/blob/master/MNIST/MNIST_data_csv.zip?raw=true'
r = requests.get(url)
with open('MNIST_data_csv.zip', 'wb') as f:
    f.write(r.content)
import zipfile
azip = zipfile.ZipFile('MNIST_data_csv.zip')
azip.extractall()
# %%
import pandas as pd
mnist_train_images = pd.read_csv('mnist_train_images.csv', header=None).values
mnist_test_images = pd.read_csv('mnist_test_images.csv', header=None).values
mnist_train_labels = pd.read_csv('mnist_train_labels.csv', header=None).values
mnist_test_labels = pd.read_csv('mnist_test_labels.csv', header=None).values

# %%
import numpy as np

X_train = np.array([img.reshape(28, 28) for img in mnist_train_images])
X_test = np.array([img.reshape(28, 28) for img in mnist_test_images])
# add channel,因为是灰度图像，所以 num_channels=1
X_train=np.expand_dims(X_train, 3)
X_test=np.expand_dims(X_test, 3)
Y_train = mnist_train_labels
Y_test = mnist_test_labels

# %%
data_size,image_width, image_height,num_channels = X_train.shape
target_size = mnist_train_labels.shape[1]

conv1_features = 25
conv2_features = 50
max_pool_size1 = 2
max_pool_size2 = 2
fully_connected_size1 = 100

# %%
import tensorflow as tf


x = tf.placeholder(dtype=tf.float32, shape=(None, image_width, image_height, num_channels))
y = tf.placeholder(dtype=tf.float32, shape=(None, target_size))


# 卷积+ReLu+池化+卷积+ReLu+池化
conv1_weight = tf.Variable(tf.truncated_normal(shape=(4, 4, num_channels, conv1_features), stddev=0.1))
conv1_bias = tf.Variable(tf.zeros(shape=(conv1_features)))

conv1 = tf.nn.conv2d(x, conv1_weight, strides=(1, 1, 1, 1), padding='SAME')
relu1 = tf.nn.relu(conv1 + conv1_bias)
max_pool1 = tf.nn.max_pool(relu1, ksize=(1, max_pool_size1, max_pool_size1, 1), strides=(1, 2, 2, 1), padding='SAME')


conv2_weight = tf.Variable(tf.truncated_normal(shape=(4, 4, conv1_features, conv2_features), stddev=0.1))
conv2_bias = tf.Variable(tf.zeros(shape=(conv2_features)))

conv2 = tf.nn.conv2d(max_pool1, conv2_weight, strides=(1, 1, 1, 1), padding='SAME')
relu2 = tf.nn.relu(conv2 + conv2_bias)
max_pool2 = tf.nn.max_pool(relu2, ksize=(1, max_pool_size2, max_pool_size2, 1), strides=(1, 2, 2, 1), padding='SAME')




# %%
# 全连接层

# 先摊平
final_conv_shape = max_pool2.get_shape().as_list()
final_shape = final_conv_shape[1] * final_conv_shape[2] * final_conv_shape[3]
flat_output = tf.reshape(tensor=max_pool2, shape=(-1, final_shape))

# 全连接层1
full1_weight = tf.Variable(tf.truncated_normal((final_shape, fully_connected_size1), stddev=0.1))
full1_bias = tf.Variable(tf.truncated_normal([1, fully_connected_size1], stddev=0.1))
fully_connected1 = tf.nn.relu(tf.matmul(flat_output, full1_weight) + full1_bias)

# dropout
keep_prob=tf.placeholder(tf.float32)
h_fc1_drop=tf.nn.dropout(fully_connected1,keep_prob)

# 全连接层2+softmax
full2_weight = tf.Variable(tf.truncated_normal((fully_connected_size1, target_size), stddev=0.1))
full2_bias = tf.Variable(tf.truncated_normal([1, target_size], stddev=0.1, dtype=tf.float32))
y_hat = tf.nn.softmax(tf.matmul(fully_connected1, full2_weight) + full2_bias)


# %%
cross_entropy = tf.reduce_mean(-tf.reduce_sum(y * tf.log(y_hat), axis=1))
train_step = tf.train.GradientDescentOptimizer(learning_rate=0.01).minimize(cross_entropy)

sess = tf.Session()
sess.run(tf.global_variables_initializer())
batch_size = 100

for i in range(2000):
    choice_indexes = np.random.choice(data_size, batch_size)
    feed_dict = {x: X_train[choice_indexes], y: Y_train[choice_indexes], keep_prob: 0.75}
    sess.run(train_step, feed_dict=feed_dict)
    if i % 100 == 0:
        value_cross_entropy = sess.run(cross_entropy, feed_dict={x: X_test[:100], y: Y_test[:100],keep_prob:1})
        print('第{i}次循环，test上的cross_entropy是{value_cross_entropy}'
              .format(i=i,value_cross_entropy=value_cross_entropy))

# 模型评价
Y_test_predict=sess.run(y_hat,feed_dict={x:X_test,keep_prob:1})
from sklearn import metrics
metrics.confusion_matrix(Y_test.argmax(axis=1),Y_test_predict.argmax(axis=1))