在pytorch的Docs中有关于nn.Conv2d的具体描述:
torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)
https://zhuanlan.zhihu.com/p/35405071
import torch
import torch.nn as nn
from torch.autograd import Variable
input = torch.ones(1, 3, 224, 224)
input = Variable(input)
f = nn.Conv2d(in_channels=3, out_channels=9, kernel_size=5, groups=3)
output = f(input)
print(output.shape) # (1, 9, 220, 220)
我们通过实际的例子加以说明:
# pytorch 0.3.0
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed May 2 20:13:05 2018
@author: huijian
"""
# experiment about groups
import torch
import torch.nn as nn
from torch.autogr