卷积神经网络—padding、 pool、 Activation layer

#coding:utf-8
import tensorflow as tf
tf.reset_default_graph()
image = tf.random_normal([1, 112, 96, 3])
in_channels = 3
out_channels = 32
kernel_size = 5
conv_weight = tf.Variable(tf.truncated_normal([kernel_size, kernel_size, in_channels, out_channels], stddev=0.1,
                                              dtype=tf.float32))

print 'image shape', image.get_shape()
print 'conv weight shape', conv_weight.get_shape()
bias = tf.Variable(tf.zeros([out_channels], dtype=tf.float32))
conv = tf.nn.conv2d(image, conv_weight, strides=[1, 3, 3, 1], padding='SAME')
conv = tf.nn.bias_add(conv, bias)
print 'conv output shape with SAME padded', conv.get_shape()

conv = tf.nn.conv2d(image, conv_weight, strides=[1, 3, 3, 1], padding='VALID')
conv = tf.nn.bias_add(conv, bias)
print 'conv output shape with VALID padded', conv.get_shape()


'''
两种padding方式的不同
SAME 简而言之就是丢弃，像素不够的时候对那部分不进行卷积，输出图像的宽高计算公式如下(向上取整，进1)：
HEIGHT = ceil(float(in_height)/float(strides[1]))
WIDTH = ceil(float(in_width)/float(strides[2]))

VALID 简而言之就是补全，像素不够的时候补0，输出图像的宽高计算公式如下
HEIGHT = ceil(float(in_height - filter_height + 1)/float(strides[1]))
WIDTH = ceil(float(in_width - filter_width + 1)/float(strides[2]))
'''

 打印结果

 image shape (1, 112, 96, 3)
 conv weight shape (5, 5, 3, 32)
 conv output shape with SAME padded (1, 38, 32, 32)
 conv output shape with VALID padded (1, 36, 31, 32)

pool_size = 3
pool = tf.nn.max_pool(conv, ksize=[1, pool_size, pool_size, 1], strides=[1, 2, 2, 1], padding='SAME')
print pool.get_shape()
pool = tf.nn.max_pool(conv, ksize=[1, pool_size, pool_size, 1], strides=[1, 2, 2, 1], padding='VALID')
print pool.get_shape()

结果

(1, 18, 16, 32)
(1, 17, 15, 32)

#激活层
relu = tf.nn.relu(pool)
print relu.get_shape()
l2_regularizer = tf.contrib.layers.l2_regularizer(1.0)
def prelu(x, name = 'prelu'):
    with tf.variable_scope(name):
        alphas = tf.get_variable('alpha', x.get_shape()[-1], initializer=tf.constant_initializer(0.25), regularizer=l2_regularizer, dtype=
                                 tf.float32)
    pos = tf.nn.relu(x)
    neg = tf.multiply(alphas, (x - abs(x)) * 0.5)
    return pos + neg
prelu_out = prelu(pool)
print prelu_out.get_shape()