运用tensorflow内置卷积函数tf.nn.conv2d(input,filter,strides,padding,name=None)对图像进行低卷积处理。
conv2d中的参数为:
input:输入的图像(张量)大小为[batch,in_height,in_width,in_channels]
filter:卷积核,大小为[filter_height,filter_width,in_channels,out_channels]
strides:为步长。大小为:[1,stride_h,stride_w,1]
padding:表示对输入图像进行0填充。可选为:SAME(此时输入与输出的大小完全相同),VALID:对输入图像不进行0填充。
实例代码:
import tensorflow as tf
import numpy as np
import cv2
import matplotlib.pyplot as plt
img = cv2.imread("C:\\lena1.png")
plt.subplot(1,2,1)
plt.imshow(img)
img = np.array(img,dtype = "float32")
x_image = tf.reshape(img,[1,512,512,3])
filter = tf.Variable(tf.ones([7,7,3,1]))
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
res = tf.nn.conv2d(x_image,filter,[1,2,2,1],padding = "SAME")
res_image = sess.run(tf.reshape(res,[256,256])) / 128 + 1
plt.subplot(1,2,2)
plt.imshow(res_image)
plt.show()
cv2.imshow("lena",res_image.astype("uint8"))
cv2.waitKey()
输出显示: