AI作业7

1、简单描述卷积、卷积核、多通道、特征图、特征选择概念。

        卷积：系统某一时刻的输出是由多个输入共同作用（叠加）的结果。

        卷积核：可以看作对某个局部的加权求和。

        多通道：输入数据和卷积核具有多个通道。

        特征图：卷积操作后得到的输出数据。

        特征选择：通过不同的卷积核提取不同的特征，从而得到更好的模型表现。

2、边缘检测

import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
from PIL import Image
import matplotlib.pyplot as plt
 
plt.rcParams['font.sans-serif'] = ['SimHei'] 
plt.rcParams['axes.unicode_minus'] = False  
file_path = 'tree.jpg'
im = Image.open(file_path).convert('L')  
im = np.array(im, dtype='float32')  # 将其转换为一个矩阵
print(im.shape[0], im.shape[1])
 
plt.imshow(im.astype('uint8'), cmap='gray')  # 可视化图片
plt.title('原图')
plt.show()
 
im = torch.from_numpy(im.reshape((1, 1, im.shape[0], im.shape[1])))
conv1 = nn.Conv2d(1, 1, 3 ,bias=False,padding=1)  # 定义卷积
 
sobel_kernel = np.array([[-1, -1, -1],
                  [-1,  8, -1],
                  [-1, -1, -1]], dtype='float32')  # 定义轮廓检测算子
sobel_kernel = sobel_kernel.reshape((1, 1, 3, 3))  # 适配卷积的输入输出
conv1.weight.data = torch.from_numpy(sobel_kernel)  # 给卷积的 kernel 赋值
 
edge1 = conv1(Variable(im))  # 作用在图片上
for i in range(edge1.shape[2]):
    for j in range(edge1.shape[3]):
        if edge1[0][0][i][j]>255:
            edge1[0][0][i][j]=255
        if edge1[0][0][i][j]<0:
            edge1[0][0][i][j]=0
x = edge1.data.squeeze().numpy()
print(x.shape)  # 输出大小
 
plt.imshow(x, cmap='gray')
plt.show()

   

锐化

import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
from PIL import Image
import matplotlib.pyplot as plt
 
plt.rcParams['font.sans-serif'] = ['SimHei'] 
plt.rcParams['axes.unicode_minus'] = False  
file_path = 'tree.jpg'
im = Image.open(file_path).convert('L')  
im = np.array(im, dtype='float32')  # 将其转换为一个矩阵
print(im.shape[0], im.shape[1])
 
plt.imshow(im.astype('uint8'), cmap='gray')  # 可视化图片
plt.title('原图')
plt.show()
 
im = torch.from_numpy(im.reshape((1, 1, im.shape[0], im.shape[1])))
conv1 = nn.Conv2d(1, 1, 3 ,bias=False,padding=1)  # 定义卷积
 
sobel_kernel = np.array([[0, -1, 0],
                         [-1, 5, -1],
                         [0, -1,0]], dtype='float32')  # 定义轮廓检测算子
sobel_kernel = sobel_kernel.reshape((1, 1, 3, 3))  # 适配卷积的输入输出
conv1.weight.data = torch.from_numpy(sobel_kernel)  # 给卷积的 kernel 赋值
 
edge1 = conv1(Variable(im))  # 作用在图片上
for i in range(edge1.shape[2]):
    for j in range(edge1.shape[3]):
        if edge1[0][0][i][j]>255:
            edge1[0][0][i][j]=255
        if edge1[0][0][i][j]<0:
            edge1[0][0][i][j]=0
x = edge1.data.squeeze().numpy()
print(x.shape)  # 输出大小
 
plt.imshow(x, cmap='gray')
plt.show()

 

 

模糊

import numpy as np
import torch
from torch import nn
from torch.autograd import Variable
from PIL import Image
import matplotlib.pyplot as plt
 
plt.rcParams['font.sans-serif'] = ['SimHei'] 
plt.rcParams['axes.unicode_minus'] = False  
file_path = 'tree.jpg'
im = Image.open(file_path).convert('L')  
im = np.array(im, dtype='float32')  # 将其转换为一个矩阵
print(im.shape[0], im.shape[1])
 
plt.imshow(im.astype('uint8'), cmap='gray')  # 可视化图片
plt.title('原图')
plt.show()
 
im = torch.from_numpy(im.reshape((1, 1, im.shape[0], im.shape[1])))
conv1 = nn.Conv2d(1, 1, 3 ,bias=False,padding=1)  # 定义卷积
 
sobel_kernel = np.array([[0.0625, 0.125, 0.0625],
                         [0.125, 0.25, 0.125],
                         [0.0625, 0.125,0.0625]], dtype='float32')
sobel_kernel = sobel_kernel.reshape((1, 1, 3, 3))  # 适配卷积的输入输出
conv1.weight.data = torch.from_numpy(sobel_kernel)  # 给卷积的 kernel 赋值
 
edge1 = conv1(Variable(im))  # 作用在图片上
for i in range(edge1.shape[2]):
    for j in range(edge1.shape[3]):
        if edge1[0][0][i][j]>255:
            edge1[0][0][i][j]=255
        if edge1[0][0][i][j]<0:
            edge1[0][0][i][j]=0
x = edge1.data.squeeze().numpy()
print(x.shape)  # 输出大小
 
plt.imshow(x, cmap='gray')
plt.show()