卷积神经网络（上）——卷积算子应用例子

 物体边缘检测：使用多输出通道，当图像读入时，先将其转换为float32的numpy.ndarray，然后图像转换为【H,W,3】的形状，以【N,C,H,W】的数据维度输出图片

卷积核大小设置为3×3

输入图像通道数3

输出图像通道数1

import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
import paddle
from paddle.nn import Conv2D
from paddle.nn.initializer import Assign
img = Image.open('E:/pycharm/paddleCNN/picture/206.jpg')
w = np.array([[-1, -1, -1], [-1, 8, -1], [-1, -1, -1]], dtype='float32') / 8
w = w.reshape([1, 1, 3, 3])
w = np.repeat(w, 3, axis=1)
conv = Conv2D(in_channels=3, out_channels=1, kernel_size=[3, 3],
              weight_attr=paddle.ParamAttr(
                  initializer=Assign(value=w)))


x = np.array(img).astype('float32')
x = np.transpose(x, (2, 0, 1))
x = x.reshape(1, 3, img.height, img.width)
x = paddle.to_tensor(x)
y = conv(x)
out = y.numpy()
plt.figure(figsize=(20, 10))
f = plt.subplot(121)
f.set_title('input image', fontsize=25)
plt.imshow(img)
f = plt.subplot(122)
f.set_title('output feature map', fontsize=25)
plt.imshow(out.squeeze(), cmap='gray')
plt.savefig('exam9.jpg')
plt.show()

输入与输出图像：

图像均值模糊：

卷积核（5*5的卷积核中每个值均为1）是用当前像素跟它邻域内的像素取平均，这样可以使图像上噪声比较大的点变得更平滑

卷积核大小设置为5×5

输入图像通道数1

输出图像通道数1

import paddle
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
from paddle.nn import Conv2D
from paddle.nn.initializer import Assign
img = Image.open('E:/pycharm/paddleCNN/picture/444.jpg').convert('L')
img = np.array(img)
w = np.ones([1, 1, 5, 5], dtype = 'float32')/25
conv = Conv2D(in_channels=1, out_channels=1, kernel_size=[5, 5], weight_attr=paddle.ParamAttr(
         initializer=Assign(value=w)))
x = img.astype('float32')
x = x.reshape(1, 1, img.shape[0], img.shape[1])
x = paddle.to_tensor(x)
y = conv(x)
out = y.numpy()

plt.figure(figsize=(20, 12))
f = plt.subplot(121)
f.set_title('input image')
plt.imshow(img, cmap='gray')

f = plt.subplot(122)
f.set_title('output feature map')
out = out.squeeze()
plt.imshow(out, cmap='gray')
plt.savefig('exam6.jpg')
plt.show()