paddlepaddle学习

最新推荐文章于 2024-06-11 01:02:30 发布

qq_51086926

最新推荐文章于 2024-06-11 01:02:30 发布

阅读量1.1k

点赞数

CC 4.0 BY-SA版权

分类专栏： 1 文章标签： 1024程序员节

本文链接：https://blog.youkuaiyun.com/qq_51086926/article/details/127498112

1 专栏收录该内容

9 篇文章

订阅专栏

该博客通过三个实例展示了如何利用PaddlePaddle库进行卷积操作。首先，介绍了一个简单的1x3卷积核用于黑白边界检测；接着，应用3x3卷积核实现图像物体边缘检测；最后，演示了如何用相同卷积核实现图像的均值模糊效果。所有示例都配合Matplotlib显示了输入图像和处理后的特征图。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

卷积算子例1-

黑白边界检测

代码:

import matplotlib.pyplot as plt
import numpy as np
import paddle
from paddle.nn import Conv2D
from paddle.nn.initializer import Assign


w = np.array([1, 0, -1], dtype='float32')

w = w.reshape([1, 1, 1, 3])

conv = Conv2D(in_channels=1, out_channels=1, kernel_size=[1, 3],
       weight_attr=paddle.ParamAttr(
          initializer=Assign(value=w)))


img = np.ones([50,50], dtype='float32')
img[:, 30:] = 0.

x = img.reshape([1,1,50,50])

x = paddle.to_tensor(x)

y = conv(x)

out = y.numpy()
f = plt.subplot(121)
f.set_title('input image', fontsize=15)
plt.imshow(img, cmap='gray')
f = plt.subplot(122)
f.set_title('output featuremap', fontsize=15)

plt.imshow(out.squeeze(), cmap='gray')
plt.show()

print(conv.weight)

print(conv.bias)

结果：

例2-

图像物体边缘检测

代码：

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('./work/image/toy.jpg')

# 设置卷积核参数
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)))

# 将读入的图片转化为float32类型的numpy.ndarray
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=15)
plt.imshow(img)
f = plt.subplot(122)
f.set_title('output feature map', fontsize=15)
plt.imshow(out.squeeze(), cmap='gray')
plt.show()

结果图：

例3-

图像均值模糊

代码：

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('./work/image/toy.jpg')

# 设置卷积核参数
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)))

# 将读入的图片转化为float32类型的numpy.ndarray
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=15)
plt.imshow(img)
f = plt.subplot(122)
f.set_title('output feature map', fontsize=15)
plt.imshow(out.squeeze(), cmap='gray')
plt.show()

结果图：