对于B站课程19_P3
'''卷积层'''
import torch
from torch import nn
from d2l import torch as d2l
# 互相关运算
def corr2d(X, K):
"""计算二维互相关运算"""
h, w = K.shape
Y = torch.zeros((X.shape[0] - h + 1, X.shape[1] - w + 1))
for i in range(Y.shape[0]):
for j in range(Y.shape[1]):
Y[i, j] = (X[i:i + h, j:j + w] * K).sum()
return Y
# 自定义二维卷积层
class Conv2D(nn.Module):
def __init__(self, kernel_size):
super().__init__()
self.weight = nn.Parameter(torch.rand(kernel_size))
self.bias = nn.Parameter(torch.zeros(1))
def forward(self, x):
return corr2d(x, self.weight) + self.bias
if __name__ == '__main__':
'''
X = torch.tensor([[0.0, 1.0, 2.0], [3.0, 4.0, 5.0], [6.0, 7.0, 8.0]])
K = torch.tensor([[0.0, 1.0], [2.0, 3.0]])
print(corr2d(X, K))
'''
X = torch.ones((6, 8))
X[:, 2:6] = 0
K = torch.tensor([[1.0, -1.0]]) # 1*2的卷积核
Y = corr2d(X, K)
print(Y)
# 构造一个二维卷积层,它具有1个输入通道1个输出通道 卷积核形状为(1,2)
conv2d = nn.Conv2d(1, 1, kernel_size=(1, 2), bias=False)
# 这个二维卷积层使用四维输入和输出格式(批量大小、通道、高度、宽度),其中批量大小和通道数都为1
X = X.reshape((1, 1, 6, 8))
Y = Y.reshape((1, 1, 6, 7))
lr = 3e-2 # 学习率
for i in range(10):
Y_hat = conv2d(X)
l = (Y_hat - Y) ** 2
conv2d.zero_grad()
l.sum().backward()
# 迭代卷积核
conv2d.weight.data[:] -= lr * conv2d.weight.grad
if (i + 1) % 2 == 0: # 每两个batch输出l.sum
print(f'epoch {i + 1}, loss {l.sum():.3f}')
print(conv2d.weight.data.reshape((1, 2)))
笔记
对于B站课程20_P2
'''填充和步幅'''
import torch
from torch import nn
# 为了方便起见,我们定义了一个计算卷积层的函数。
# 此函数初始化卷积层权重,并对输入和输出提高和缩减相应的维数
def comp_conv2d(conv2d, X):
# 这里的(1,1)表示批量大小和通道数都是1
X = X.reshape((1, 1) + X.shape)
Y = conv2d(X)
# 省略前两个维度:批量大小和通道
return Y.reshape(Y.shape[2:])
# return Y # torch.Size([1, 1, 8, 8])
if __name__ == '__main__':
X = torch.rand(size=(8, 8))
'''
# 步幅
conv2d = nn.Conv2d(1, 1, kernel_size=(3,3), padding=1) # 上下左右各填充一行
print(comp_conv2d(conv2d, X).shape)
conv2d = nn.Conv2d(1, 1, kernel_size=(5, 3), padding=(2, 1)) # 上下各加2行,左右各加1行。
print(comp_conv2d(conv2d, X).shape)
'''
'''
# 填充
conv2d = nn.Conv2d(1, 1, kernel_size=(3,3), padding=1, stride=(2,2))
print(comp_conv2d(conv2d, X).shape)
'''
conv2d = nn.Conv2d(1, 1, kernel_size=(3, 5), padding=(0, 1), stride=(3, 4))
print(comp_conv2d(conv2d, X).shape)
对于B站课程21_P2
'''多输入多输出'''
import torch
from d2l import torch as d2l
# 多输入通道,单输出通道
def corr2d_multi_in(X, K):
# 先遍历“X”和“K”的第0个维度(通道维度),再把它们加在一起
return sum(d2l.corr2d(x, k) for x, k in zip(X, K)) # zip 依次返回X单个通道及其对应的kernal
# 多输入,多输出通道
def corr2d_multi_in_out(X, K):
# 迭代“K”的第0个维度,每次都对输入“X”执行互相关运算。
# 最后将所有结果都叠加在一起
return torch.stack([corr2d_multi_in(X, k) for k in K], 0)
# 1*1的卷积(等价于全连接)
def corr2d_multi_in_out_1x1(X, K):
c_i, h, w = X.shape # c_i,h, w=3,
c_o = K.shape[0] # c_o=2
X = X.reshape((c_i, h * w)) # 3*9
K = K.reshape((c_o, c_i)) # 2*3
# 全连接层中的矩阵乘法
Y = torch.matmul(K, X)
return Y.reshape((c_o, h, w))
if __name__ == '__main__':
'''
# 多输入单\多输出
X = torch.tensor([[[0.0, 1.0, 2.0], [3.0, 4.0, 5.0], [6.0, 7.0, 8.0]],
[[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]])
K = torch.tensor([[[0.0, 1.0], [2.0, 3.0]], [[1.0, 2.0], [3.0, 4.0]]])
# K + 1:对K的每个元素+1,把K,K + 1, K + 2 按dim=0即按行堆叠起来
K = torch.stack((K, K + 1, K + 2), 0)
# K.shape torch.Size([3, 2, 2, 2]) 3表示个输出,第一个2对应输入有2个通道,即原来的K.shape为[2,2,2]
#print(corr2d_multi_in(X, K)) # 多输入单输出
print(corr2d_multi_in_out(X, K)) # 多输入多输出
'''
# 1*1的卷积(3输入2输出)
X = torch.normal(0, 1, (3, 3, 3))
K = torch.normal(0, 1, (2, 3, 1, 1))
Y1 = corr2d_multi_in_out_1x1(X, K)
Y2 = corr2d_multi_in_out(X, K)
assert float(torch.abs(Y1 - Y2).sum()) < 1e-6
对于B站课程22_P2
'''池化'''
import torch
from torch import nn
from d2l import torch as d2l
def pool2d(X, pool_size, mode='max'): # 该函数第三个参数有默认值可不传
p_h, p_w = pool_size
Y = torch.zeros((X.shape[0] - p_h + 1, X.shape[1] - p_w + 1))
for i in range(Y.shape[0]):
for j in range(Y.shape[1]):
if mode == 'max':
Y[i, j] = X[i: i + p_h, j: j + p_w].max()
elif mode == 'avg':
Y[i, j] = X[i: i + p_h, j: j + p_w].mean()
return Y
'''
# 池化
X = torch.tensor([[0.0, 1.0, 2.0], [3.0, 4.0, 5.0], [6.0, 7.0, 8.0]])
print(pool2d(X, (2, 2)))
print(pool2d(X, (2, 2), 'avg'))
'''
X = torch.arange(16, dtype=torch.float32).reshape((1, 1, 4, 4)) # 第1个1批量大小 第2个1通道个数
print(X)
'''
# 单通道池化+步幅、填充
pool2d = nn.MaxPool2d(2) # torch中默认步幅和池化层大小相同
print(pool2d(X))
pool2d = nn.MaxPool2d(3, padding=1, stride=2) # 大小3*3 填充上下左右各1,步幅为2
print(pool2d(X))
pool2d = nn.MaxPool2d((2, 3), stride=(2, 3), padding=(1, 1))
print(pool2d(X))
'''
# 多通道输入池化
X = torch.cat((X, X + 1), 1) # cat不增加维度
print(X)
pool2d = nn.MaxPool2d(3, padding=1, stride=2)
print(pool2d(X))
对于21_P2中.stack与22_P2.cat的理解
.cat不增加维度
.stack会增加维度