卷积网络的基本公式:
W矩阵 * X矩阵 +B 矩阵 =Y矩阵
其中X是输入项,W和B根据BP算法调整
对于一个卷积,定义一个占位符
x = tf.placeholder(tf.float32, [None, w*h])
wc=tf.Variable(tf.random_normal([3, 3, 1, 64])
#3 3 分别为3x3大小的卷积核 1位输入数目 因为是第一层所以是1 输出我们配置的64
# 所以我们知道了 如果下一次卷积wc2=[5,5,64,256] //5x5 是我们配置的卷积核大小,第三位表示输入数目 我们通过上面知道 上面的输出 也就是下一层的输入 所以 就是64*64 输出我们定义成256 这个随你喜好,关键要迭代看效果,一般都是某一个v*v的值
b1=tf.Variable(tf.random_normal([64]))
# 同样可以知道b2=[256]
参照别人的博客,在alexnet增加一层:
# -*- coding:UTF-8 -*-
#导入input_data用于自动下载和安装MNIST数据集
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
import tensorflow as tf
learning_rate = 0.001
training_iters = 3000
batch_size = 64
display_step = 20
n_input = 28*28
n_classes = 10
dropout = 0.8
x = tf.placeholder(tf.float32, [None, n_input])
y = tf.placeholder(tf.float32, [None, n_classes])
keep_prob = tf.placeholder(tf.float32) # dropout (keep probability)
def conv2d(name, l_input, w, b):
return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
def max_pool(name, l_input, k):
return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
def norm(name, l_input, lsize=4):
return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
def customnet(_X, _weights, _biases, _dropout):
_X = tf.reshape(_X, shape=[-1, 28, 28, 1])
conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
pool1 = max_pool('pool1', conv1, k=2)
norm1 = norm('norm1', pool1, lsize=4)
norm1 = tf.nn.dropout(norm1, _dropout)
conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
pool2 = max_pool('pool2', conv2, k=2)
norm2 = norm('norm2', pool2, lsize=4)
norm2 = tf.nn.dropout(norm2, _dropout)
conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
pool3 = max_pool('pool3', conv3, k=2)
norm3 = norm('norm3', pool3, lsize=4)
norm3 = tf.nn.dropout(norm3, _dropout)
conv4 = conv2d('conv4', norm3, _weights['wc4'], _biases['bc4'])
pool4 = max_pool('pool4', conv4, k=2)
norm4 = norm('norm4', pool4, lsize=4)
norm4 = tf.nn.dropout(norm4, _dropout)
dense1 = tf.reshape(norm4, [-1, _weights['wd1'].get_shape().as_list()[0]]) # Reshape conv3 output to fit dense layer input
dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1') # Relu activation
dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation
out = tf.matmul(dense2, _weights['out']) + _biases['out']
return out
weights = {
'wc1': tf.Variable(tf.random_normal([3, 3, 1, 64])),
'wc2': tf.Variable(tf.random_normal([3, 3, 64, 128])),
'wc3': tf.Variable(tf.random_normal([3, 3, 128, 256])),
'wc4': tf.Variable(tf.random_normal([2, 2, 256, 512])),
'wd1': tf.Variable(tf.random_normal([2*2*512, 1024])),
'wd2': tf.Variable(tf.random_normal([1024, 1024])),
'out': tf.Variable(tf.random_normal([1024, 10]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([64])),
'bc2': tf.Variable(tf.random_normal([128])),
'bc3': tf.Variable(tf.random_normal([256])),
'bc4': tf.Variable(tf.random_normal([512])),
'bd1': tf.Variable(tf.random_normal([1024])),
'bd2': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_classes]))
}
pred = customnet(x, weights, biases, keep_prob)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
step = 1
while step * batch_size < training_iters:
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
if step % display_step == 0:
acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc)
step += 1
print "Optimization Finished!"
print "Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.})
Ref:
https://my.oschina.net/yilian/blog/661218
https://my.oschina.net/yilian/blog/661409