2021寒假（9）

任务：

　　继续TensorFlow的学习：卷积神经网络

问题：　　　　　　　

 

 　　由报错位置可知是参数的问题，‘wc2’设置有误，卷积的参数应该是[3,3,64,128],而不是[3,3,64,64]

 

 

 　　该方法的使用发生了改变，需要改成错误提示中的形式

 

 

 

 源代码：

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# 卷积层参数和全连接层参数
n_input = 784
n_output = 10
weights = {
    'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64], stddev=0.1)),  # 3 3 1 64 h,w.输入深度,得出的特征图的个数
    'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128], stddev=0.1)),  # 64:输入深度  128:输出深度
    '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)),

}


# 特征图计算
# 转化成向量
# 卷积+池化操作
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)

    _dense1 = tf.reshape(_pool_dr2, [-1, _w['wd1'].get_shape().as_list()[0]])
    _fc1 = tf.nn.relu(tf.add(tf.matmul(_dense1, _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, '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')
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(logits=_pred, labels=y))
optm = tf.train.AdadeltaOptimizer(learning_rate=0.001).minimize(cost)
_corr = tf.equal(tf.arg_max(_pred, 1), tf.arg_max(y, 1))
accr = tf.reduce_mean(tf.cast(_corr, tf.float32))
init = tf.global_variables_initializer()

print('GRAPH READY')

mnist = input_data.read_data_sets('data/', one_hot=True)
init = tf.global_variables_initializer()
# 加载数据
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.}) / 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))
print("OPTIMIZATION FINISHED")

参考资料：

https://blog.csdn.net/qq_36447181/article/details/80279802