[pytorch]常用的函数

卷积

Conv2d(in_channels, out_channels, kernel_size, stride=1,padding=0,
dilation=1, groups=1,bias=True, padding_mode=‘zeros’)

池化

class torch.nn.MaxPool2d(kernel_size, stride=None, 
padding=0,dilation=1, return_indices=False, ceil_mode=False)

transform

torchvision.transforms.Normalize(mean, std, inplace=False)

拼接

C = torch.cat( (A,B),0 )  #按维数0拼接（竖着拼）
C = torch.cat( (A,B),1 )  #按维数1拼接（横着拼）

拼接指定的那个dim维度必须相同

import torch

A = torch.ones(2, 3)
B = 2*torch.ones(4, 3)

print("A = ", A)
print("B = ", B)

C = torch.cat([A, B], dim=0)
print("C = ", C)