卷积神经网络（Convolutional Neural Network，CNN）
- 受生物学上感受野机制的启发而提出。
- 一般是由卷积层、汇聚层和全连接层交叉堆叠而成的前馈神经网络
- 有三个结构上的特性：局部连接、权重共享、汇聚。
- 具有一定程度上的平移、缩放和旋转不变性。
- 和前馈神经网络相比，卷积神经网络的参数更少。
- 主要应用在图像和视频分析的任务上，其准确率一般也远远超出了其他的神经网络模型。
- 近年来卷积神经网络也广泛地应用到自然语言处理、推荐系统等领域。
5.1 卷积
5.1.1 二维卷积运算
5.1.2 二维卷积算子
import torch
import torch.nn as nn
class Conv2D(nn.Module):
def __init__(self, weight_attr=torch.tensor([[0., 1.], [2., 3.]])):
super(Conv2D, self).__init__()
# 使用'torch.Parameter'进行参数初始化
self.weight = torch.nn.Parameter(weight_attr)
def forward(self, X):
"""
输入：
- X：输入矩阵，shape=[B, M, N]，B为样本数量
输出：
- output：输出矩阵
"""
u, v = self.weight.shape
output = torch.zeros([X.shape[0], X.shape[1] - u + 1, X.shape[2] - v + 1])
for i in range(output.shape[1]):
for j in range(output.shape[2]):
output[:, i, j] = torch.sum(X[:, i:i + u, j:j + v] * self.weight, dim=[1, 2])
return output
# 随机构造一个二维输入矩阵
torch.random.manual_seed(100)
inputs = torch.tensor([[[1., 2., 3.], [4., 5., 6.], [7., 8., 9.]]])
conv2d = Conv2D()
outputs = conv2d(inputs)
print("input: {}, \noutput: {}".format(inputs, outputs))
input: tensor([[[1., 2., 3.],
[4., 5., 6.],
[7., 8., 9.]]]),
output: tensor([[[25., 31.],
[43., 49.]]], grad_fn=<CopySlices>)
5.1.3 二维卷积的参数量和计算量
随着隐藏层神经元数量的变多以及层数的加深，使用全连接前馈网络处理图像数据时，参数量会急剧增加。
如果使用卷积进行图像处理，相较于全连接前馈网络，参数量少了非常多。
5.1.4 感受野
5.1.5 卷积的变种
5.1.5.1 步长（Stride）
5.1.5.2 零填充（Zero Padding）
关于这几个
5.1.6 带步长和零填充的二维卷积算子
import torch
import torch.nn as nn
class Conv2D(nn.Module):
def __init__(self, kernel_size, stride=1, padding=0, weight_attr=False):
super(Conv2D, self).__init__()
if type(weight_attr) == bool:
weight_attr = torch.ones(size=(kernel_size, kernel_size))
self.weight = torch.nn.Parameter(weight_attr)
# 步长
self.stride = stride
# 零填充
self.padding = padding
def forward(self, X):
# 零填充
new_X = torch.zeros([X.shape[0], X.shape[1] + 2 * self.padding, X.shape[2] + 2 * self.padding])
new_X[:, self.padding:X.shape[1] + self.padding, self.padding:X.shape[2] + self.padding] = X
u, v = self.weight.shape
output_w = (new_X.shape[1] - u) // self.stride + 1
output_h = (new_X.shape[2] - v) // self.stride + 1
output = torch.zeros([X.shape[0], output_w, output_h])
for i in range(0, output.shape[1]):
for j in range(0, output.shape[2]):
output[:, i, j] = torch.sum(
new_X[:, self.stride * i:self.stride * i + u, self.stride * j:self.stride * j + v] * self.weight,
dim=[1, 2])
return output
inputs = torch.randn(size=[2, 8, 8])
conv2d_padding = Conv2D(kernel_size=3, padding=1,weight_attr=torch.zeros((3,3)))
outputs = conv2d_padding(inputs)
print(
"When kernel_size=3, padding=1 stride=1, input's shape: {}, output's shape: {}".format(inputs.shape, outputs.shape))
conv2d_stride = Conv2D(kernel_size=3, stride=2, padding=1)
outputs = conv2d_stride(inputs)
print(
"When kernel_size=3, padding=1 stride=2, input's shape: {}, output's shape: {}".format(inputs.shape, outputs.shape))
When kernel_size=3, padding=1 stride=1, input's shape: torch.Size([2, 8, 8]), output's shape: torch.Size([2, 8, 8])
When kernel_size=3, padding=1 stride=2, input's shape: torch.Size([2, 8, 8]), output's shape: torch.Size([2, 4, 4])
5.1.7 使用卷积运算完成图像边缘检测任务
【使用pytorch实现图像边缘检测】
import torch
import torch.nn as nn
class Conv2D(nn.Module):
def __init__(self, kernel_size, stride=1, padding=0, weight_attr=False):
super(Conv2D, self).__init__()
if type(weight_attr) == bool:
weight_attr = torch.ones(size=(kernel_size, kernel_size))
self.weight = torch.nn.Parameter(weight_attr)
# 步长
self.stride = stride
# 零填充
self.padding = padding
def forward(self, X):
# 零填充
new_X = nn.ZeroPad2d(1)(X)
u, v = self.weight.shape
output_w = (new_X.shape[1] - u) // self.stride + 1
output_h = (new_X.shape[2] - v) // self.stride + 1
output = torch.zeros([X.shape[0], output_w, output_h])
for i in range(0, output.shape[1]):
for j in range(0, output.shape[2]):
output[:, i, j] = torch.sum(
new_X[:, self.stride * i:self.stride * i + u, self.stride * j:self.stride * j + v] * self.weight,
dim=[1, 2])
return output
import matplotlib.pyplot as plt
from PIL import Image
import numpy as np
def main():
# 读取图片
img = Image.open('number.jpg').convert('L').resize((256, 256))
# 设置卷积核参数
w = np.array([[-1, -1, -1], [-1, 8, -1], [-1, -1, -1]], dtype='float32')
# 创建卷积算子，卷积核大小为3x3，并使用上面的设置好的数值作为卷积核权重的初始化参数
conv = Conv2D(kernel_size=3, stride=1, padding=0, weight_attr=torch.tensor(w))
# 将读入的图片转化为float32类型的numpy.ndarray
inputs = np.array(img).astype('float32')
print("bf to_tensor, inputs:", inputs)
# 将图片转为Tensor
inputs = torch.tensor(inputs)
print("bf unsqueeze, inputs:", inputs)
inputs = torch.unsqueeze(inputs, dim=0)
print("af unsqueeze, inputs:", inputs)
outputs = conv.forward(inputs)
outputs = outputs.squeeze()
outputs =outputs.data.detach().numpy()
# 可视化结果
plt.imshow(img)
plt.title('input image', fontsize=15)
plt.show()
plt.imshow(outputs, cmap='gray')
plt.title('output feature map', fontsize=15)
plt.show()
if __name__ == "__main__":
main()
bf to_tensor, inputs: [[159. 145. 175. ... 46. 47. 49.]
[210. 217. 119. ... 47. 45. 48.]
[ 90. 95. 68. ... 62. 43. 47.]
...
[ 28. 28. 26. ... 63. 50. 40.]
[ 27. 27. 27. ... 28. 28. 31.]
[ 27. 27. 24. ... 32. 31. 32.]]
bf unsqueeze, inputs: tensor([[159., 145., 175., ..., 46., 47., 49.],
[210., 217., 119., ..., 47., 45., 48.],
[ 90., 95., 68., ..., 62., 43., 47.],
...,
[ 28., 28., 26., ..., 63., 50., 40.],
[ 27., 27., 27., ..., 28., 28., 31.],
[ 27., 27., 24., ..., 32., 31., 32.]])
af unsqueeze, inputs: tensor([[[159., 145., 175., ..., 46., 47., 49.],
[210., 217., 119., ..., 47., 45., 48.],
[ 90., 95., 68., ..., 62., 43., 47.],
...,
[ 28., 28., 26., ..., 63., 50., 40.],
[ 27., 27., 27., ..., 28., 28., 31.],
[ 27., 27., 24., ..., 32., 31., 32.]]])
tensor([[[ 700., 280., 665., ..., 124., 141., 252.],
[ 974., 675., -83., ..., -122., -29., 153.],
[ 68., -142., -329., ..., -128., -55., 148.],
...,
[ 96., 18., 0., ..., -297., -312., -86.],
[ 79., 2., -73., ..., -93., -83., 67.],
[ 135., 84., -20., ..., 109., 97., 166.]]],
grad_fn=<CopySlices>)
ps:以上来自不是蒋承翰的博客
复现论文 Holistically-Nested Edge Detection，发表于 CVPR 2015
一个基于深度学习的端到端边缘检测模型。
虽然数据集导入成功了但是这单薄的显存告诉我这个模型看看就好
RuntimeError: CUDA out of memory. Tried to allocate 14.00 MiB (GPU 0; 1024.00 MiB total capacity; 459.71 MiB already allocated; 4.11 MiB free; 26.29 MiB cached)
看了这个时间真是离谱，还是在有好的显卡的情况下，我就算了吧，刚看有人发布了一个预训练模型接下来看看能不能用
https://github.com/meteorshowers/hed
330
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
