CNN (tensorflow,mnist)-實例4

本實例是使用tensorflow構建的CNN兩層網絡，用的數據集是mnist數據集。此數據集尾部有分享鏈接，如果代碼中通過tensorflow下載失敗，可以通過此鏈接下載好

# cnn.py文件
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
import input_data 

mnist = input_data.read_data_sets('data/', one_hot=True)  # one_hot=True表示編碼格式爲0/1編碼
trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels
print ("MNIST ready")

n_input = 784 #輸入的圖片大小28x28x1
n_output = 10 #10分類
#[3(filter的h), 3(filter的w), 1(深度，因爲是灰度圖，所以是1 ), 64(想要得到64張特徵圖,即輸出的深度)] 。'wc1'和'wc2'表示卷積層參數，'wd1'和'wd2'表示全連接層參數
weights = {
    'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)), 
    'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)),
    'wd1': tf.Variable(tf.random_normal([7 * 7 * 128, 1024], stddev=0.1)),
    'wd2': tf.Variable(tf.random_normal([1024, n_output], stddev=0.1))
    }
biases = {
    'bc1': tf.Variable(tf.random_normal([64], stddev=0.1)),
    'bc2': tf.Variable(tf.random_normal([128], stddev=0.1)),
    'bd1': tf.Variable(tf.random_normal([1024], stddev=0.1)),
    'bd2': tf.Variable(tf.random_normal([n_output], stddev=0.1))
    }

#前向傳播
def conv_basic(_input, _w, _b, _keepratio):
    # INPUT 將_input轉化成tensorflow支持的格式
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
    # CONV LAYER 1，padding='SAME'表示滑動過程中不夠就自動填0
    _conv1 = tf.nn.conv2d(_input_r, _w['wc1'], strides=[1, 1, 1, 1], padding='SAME')
    #_mean, _var = tf.nn.moments(_conv1, [0, 1, 2])
    #_conv1 = tf.nn.batch_normalization(_conv1, _mean, _var, 0, 1, 0.0001)
    _conv1 = tf.nn.relu(tf.nn.bias_add(_conv1, _b['bc1']))
    _pool1 = tf.nn.max_pool(_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    _pool_dr1 = tf.nn.dropout(_pool1, _keepratio) #隨機刪除一些神經元節點
    # CONV LAYER 2
    _conv2 = tf.nn.conv2d(_pool_dr1, _w['wc2'], strides=[1, 1, 1, 1], padding='SAME')
    #_mean, _var = tf.nn.moments(_conv2, [0, 1, 2])
    #_conv2 = tf.nn.batch_normalization(_conv2, _mean, _var, 0, 1, 0.0001)
    _conv2 = tf.nn.relu(tf.nn.bias_add(_conv2, _b['bc2']))
    _pool2 = tf.nn.max_pool(_conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    _pool_dr2 = tf.nn.dropout(_pool2, _keepratio)
    # VECTORIZE。_dense1將_pool_dr2轉化成全連接層的輸入大小格式
    _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
    # FULLY CONNECTED LAYER 1
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _w['wd1']), _b['bd1']))
    _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
    # FULLY CONNECTED LAYER 2
    _out = tf.add(tf.matmul(_fc_dr1, _w['wd2']), _b['bd2'])
    # RETURN
    out = { 'input_r': _input_r, 'conv1': _conv1, 'pool1': _pool1, 'pool1_dr1': _pool_dr1,'conv2': _conv2, 'pool2': _pool2, 'pool_dr2': _pool_dr2, 'dense1': _dense1,
           'fc1': _fc1, 'fc_dr1': _fc_dr1, 'out': _out
           }
    return out
    print ("CNN READY")
    
a = tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1))
print (a)
a = tf.Print(a, [a], "a: ")
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
#sess.run(a)

x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_output])
keepratio = tf.placeholder(tf.float32)

# FUNCTIONS
#_pred進行一次前向傳播的結果
_pred = conv_basic(x, weights, biases, keepratio)['out']
# cost是損失值，softmax_cross_entropy_with_logits是交叉熵函數，reduce_mean求一個平均的loss
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=_pred,labels=y))
# AdamOptimizer是一種優化策略，比梯度下降要好
optm = tf.train.AdamOptimizer(learning_rate=0.001).minimize(cost)
_corr = tf.equal(tf.argmax(_pred,1), tf.argmax(y,1)) #準確率
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))  #將_corr轉化爲float類型
init = tf.global_variables_initializer() #全局初始化後才能run

# SAVER
print ("GRAPH READY")

sess = tf.Session() #開闢計算區域
sess.run(init)

training_epochs = 15 #迭代次數，每迭代一次打印一次
batch_size      = 16
display_step    = 1
for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = int(mnist.train.num_examples/batch_size)
#     total_batch = 10 #爲了省時間可以設置爲10
    # Loop over all batches
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        # Fit training using batch data。不斷運行優化器
        sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio:0.7})
        # Compute average loss
        avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})/total_batch

    # Display logs per epoch step
    if epoch % display_step == 0: 
        print ("Epoch: %03d/%03d cost: %.9f" % (epoch, training_epochs, avg_cost))
        train_acc = sess.run(accr, feed_dict={x: batch_xs, y: batch_ys, keepratio:1.})
        print (" Training accuracy: %.3f" % (train_acc))
        test_acc = sess.run(accr, feed_dict={x: testimg, y: testlabel, keepratio:1.})
        print (" Test accuracy: %.3f" % (test_acc))

print ("OPTIMIZATION FINISHED")

input_data.py文件

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import gzip
import os
import tempfile

import numpy
from six.moves import urllib
from six.moves import xrange  # pylint: disable=redefined-builtin
import tensorflow as tf
from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets

結果截圖：訓練精度爲100%，測試精度接近100%

文件目錄：

數據集分享下載鏈接：鏈接：https://pan.baidu.com/s/1-gSCEWPT17xHoObzV7deqg 
提取碼：iz3h