神经网络的基本骨架

1. nn.Module的使用

所有的模型都要继承 Module 类
需要重写初始化函数和运算步骤函数

eg：

python 复制代码

import torch.nn as nn
import torch.nn.functional as F

class Model(nn.Module):		# 继承父类Module 
    def __init__(self):		# 重写初始化函数
        super().__init__()		# 调用父类初始化
        self.conv1 = nn.Conv2d(1, 20, 5)
        self.conv2 = nn.Conv2d(20, 20, 5)

    def forward(self, x):		# 神经网络的运算步骤--前向传播
        x = F.relu(self.conv1(x))	# x->卷积->非线性
        return F.relu(self.conv2(x))	# x->卷积->非线性

代码示例：

python 复制代码

import torch
from torch import nn

class Kun(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, input):
        output = input+1	# 实现输出加1
        return output

kun = Kun()
x = torch.tensor(1.0)
output = kun(x)
print(output)   # tensor(2.)

2. 卷积

conv2可选参数

卷积计算过程示意：

python 复制代码

import torch

# 输入图像（5*5）
input = torch.tensor([[1, 2, 0, 3, 1],
                      [0, 1, 2, 3, 1],
                      [1, 2, 1, 0, 0],
                      [5, 2, 3, 1, 1],
                      [2, 1, 0, 1, 1]])  # 输入tensor数据类型的二维矩阵

# 卷积核
kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])


print(input.shape)
print(kernel.shape)

python 复制代码

torch.Size([5, 5])
torch.Size([3, 3])

如果不调整尺寸会报错：Expected 3D(unbatched) or 4D(batched) input to conv2d, but got input of size: $5, 5$

所以需要调整

python 复制代码

input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))

python 复制代码

output = F.conv2d(input, kernel, stride=1)
print(output)

--------------------------------------------------------------------------
tensor([[[[10, 12, 12],
          [18, 16, 16],
          [13,  9,  3]]]])

stride可以选择移动的步长

python 复制代码

output2 = F.conv2d(input, kernel, stride=2)
print(output2)
----------------------------------------------------------------------------
tensor([[[[10, 12],
          [13,  3]]]])

padding进行填充(默认填充0)

python 复制代码

output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)
-----------------------------------------------------------------------------
tensor([[[[ 1,  3,  4, 10,  8],
          [ 5, 10, 12, 12,  6],
          [ 7, 18, 16, 16,  8],
          [11, 13,  9,  3,  4],
          [14, 13,  9,  7,  4]]]])

示例代码：

python 复制代码

import torch
import torch.nn.functional as F
# 输入图像（5*5）
input = torch.tensor([[1, 2, 0, 3, 1],
                      [0, 1, 2, 3, 1],
                      [1, 2, 1, 0, 0],
                      [5, 2, 3, 1, 1],
                      [2, 1, 0, 1, 1]])  # 输入tensor数据类型的二维矩阵

# 卷积核
kernel = torch.tensor([[1, 2, 1],
                       [0, 1, 0],
                       [2, 1, 0]])
# 调整输入的尺寸
# 如果不调整尺寸会报错
# Expected 3D(unbatched) or 4D(batched) input to conv2d, but got input of size: [5, 5]
input = torch.reshape(input, (1, 1, 5, 5))
kernel = torch.reshape(kernel, (1, 1, 3, 3))
# print(input.shape)    # torch.Size([1, 1, 5, 5])
# print(kernel.shape)   # torch.Size([1, 1, 3, 3])

output = F.conv2d(input, kernel, stride=1)
print(output)

output2 = F.conv2d(input, kernel, stride=2)
print(output2)

output3 = F.conv2d(input, kernel, stride=1, padding=1)
print(output3)

神经网络入门

1. nn.Module的使用

2. 卷积