-
kernel_size(int or tuple):池化窗口size
-
stride(int or tuple):池化的步长
-
padding(int or tuple):池化的填充,默认为0
-
案例
pool of square window of size=3, stride=2
m = nn.MaxPool2d(3,stride = 2)
pool of non-square window
m = nn.MaxPool2d((3, 2), stride=(2, 1))
input = torch.randn(20, 16, 50, 32)
output = m(input)
-
nn.AvgPool2d(kernel_size,stride):这里列举了常用的几个参数,其余省略了
-
kernel_size(int or tuple):池化窗口size
-
stride(int or tuple):池化的步长
-
padding(int or tuple):池化的填充,默认为0
-
案例
pool of square window of size=3, stride=2
m = nn.AvgPool2d(3, stride=2)
pool of non-square window
m = nn.AvgPool2d((3, 2), stride=(2, 1))
input = torch.randn(20, 16, 50, 32)
output = m(input)
-
nn.Linear(in_features, out_features, bias)
-
in_features:输入特征数
-
out_features:输出特征数
-
bias:偏置
-
案例
m = nn.Linear(20, 30)
input = torch.randn(128, 20)
output &