python,tensorflow,CNN实现mnist数据集的训练与验证正确率

Posted 2021-02-02 C～K

1.工程目录

2.导入data和input_data.py

链接：https://pan.baidu.com/s/1EBNyNurBXWeJVyhNeVnmnA 
提取码：4nnl 

3.CNN.py

import tensorflow as tf
import matplotlib.pyplot as plt
import input_data

mnist = input_data.read_data_sets(\'data/\', one_hot=True)
trainimg = mnist.train.images
trainlabel = mnist.train.labels
testimg = mnist.test.images
testlabel = mnist.test.labels
print(\'MNIST ready\')

n_input = 784
n_output = 10


weights = {
    \'wc1\': tf.Variable(tf.truncated_normal([3, 3, 1, 64], stddev=0.1)),
    \'wc2\': tf.Variable(tf.truncated_normal([3, 3, 64, 128], stddev=0.1)),
    \'wd1\': tf.Variable(tf.truncated_normal([7*7*128, 1024], stddev=0.1)),
    \'wd2\': tf.Variable(tf.truncated_normal([1024, n_outpot], 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_outpot], stddev=0.1)),
}

def conv_basic(_input, _w, _b, _keepratio):
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
    _conv1 = tf.nn.conv2d(_input_r, _w[\'wc1\'], strides=[1, 1, 1, 1], padding=\'SAME\')
    _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)
    _conv2 = tf.nn.conv2d(_pool_dr1, _w[\'wc2\'], strides=[1, 1, 1, 1], padding=\'SAME\')
    _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)
    _densel = tf.reshape(_pool_dr2, [-1, _w[\'wd1\'].get_shape().as_list()[0]])
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_densel, _w[\'wd1\']), _b[\'bd1\']))
    _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
    _out = tf.add(tf.matmul(_fc_dr1, _w[\'wd2\']), _b[\'bd2\'])
    out = {
        \'input_r\': _input_r, \'conv1\': _conv1, \'pool1\': _pool1, \'pool_dr1\': _pool_dr1,
        \'conv2\': _conv2, \'pool2\': _pool2, \'pool_dr2\': _pool_dr2, \'densel\': _densel,
        \'fc1\': _fc1, \'fc_dr1\': _fc_dr1, \'out\': _out
    }
    return out

print(\'CNN READY\')

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

_pred = conv_basic(x, weights, biases, keepratio)[\'out\']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(_pred, y))
optm = tf.train.AdamOptimizer(learning_rate=0.01).minimize(cost)
_corr = tf.equal(tf.argmax(_pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))
init = tf.global_variables_initializer()

print(\'GRAPH READY\')

sess = tf.Session()
sess.run(init)
training_epochs = 15
batch_size = 16
display_step = 1

for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = 10
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)
        sess.run(optm, feed_dict={x: batch_xs, y: batch_ys, keepratio: 0.7})
        avg_cost += sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keepratio: 1.0})/total_batch

    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))


res_dict = {\'weight\': sess.run(weights), \'biases\': sess.run(biases)}

import pickle
with open(\'res_dict.pkl\', \'wb\') as f:
    pickle.dump(res_dict, f, pickle.HIGHEST_PROTOCOL)

4.test.py

import pickle
import numpy as np

def load_file(path, name):
    with open(path+\'\'+name+\'.pkl\', \'rb\') as f:
        return pickle.load(f)

res_dict = load_file(\'\', \'res_dict\')
print(res_dict[\'weight\'][\'wc1\'])

index = 0

import input_data
mnist = input_data.read_data_sets(\'data/\', one_hot=True)

test_image = mnist.test.images
test_label = mnist.test.labels

import tensorflow as tf

def conv_basic(_input, _w, _b, _keepratio):
    _input_r = tf.reshape(_input, shape=[-1, 28, 28, 1])
    _conv1 = tf.nn.conv2d(_input_r, _w[\'wc1\'], strides=[1, 1, 1, 1], padding=\'SAME\')
    _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)
    _conv2 = tf.nn.conv2d(_pool_dr1, _w[\'wc2\'], strides=[1, 1, 1, 1], padding=\'SAME\')
    _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)
    _densel = tf.reshape(_pool_dr2, [-1, _w[\'wd1\'].shape[0]])
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_densel, _w[\'wd1\']), _b[\'bd1\']))
    _fc_dr1 = tf.nn.dropout(_fc1, _keepratio)
    _out = tf.add(tf.matmul(_fc_dr1, _w[\'wd2\']), _b[\'bd2\'])
    out = {
        \'input_r\': _input_r, \'conv1\': _conv1, \'pool1\': _pool1, \'pool_dr1\': _pool_dr1,
        \'conv2\': _conv2, \'pool2\': _pool2, \'pool_dr2\': _pool_dr2, \'densel\': _densel,
        \'fc1\': _fc1, \'fc_dr1\': _fc_dr1, \'out\': _out
    }
    return out

n_input = 784
n_output = 10


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


keepratio = tf.placeholder(tf.float32)



_pred = conv_basic(x, res_dict[\'weight\'], res_dict[\'biases\'], keepratio)[\'out\']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(_pred, y))

_corr = tf.equal(tf.argmax(_pred, 1), tf.argmax(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))


init = tf.global_variables_initializer()

sess = tf.Session()
sess.run(init)
training_epochs = 1
batch_size = 1
display_step = 1


for epoch in range(training_epochs):
    avg_cost = 0.
    total_batch = 10
    for i in range(total_batch):
        batch_xs, batch_ys = mnist.train.next_batch(batch_size)

    if epoch % display_step == 0:
        print(\'_pre:\', np.argmax(sess.run(_pred, feed_dict={x: batch_xs, keepratio: 1. })))
        print(\'answer:\', np.argmax(batch_ys))