pytorch __init__、forward与__call__的用法小结

import torch
import torch.nn as nn
import torch.nn.functional as F
 
class Net(nn.Module):
 def __init__(self, in_channels, mid_channels, out_channels):
 super(Net, self).__init__()
 self.conv0 = torch.nn.Sequential(
 torch.nn.Conv2d(in_channels, mid_channels, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 torch.nn.LeakyReLU())
 self.conv1 = torch.nn.Sequential(
 torch.nn.Conv2d(mid_channels, out_channels * 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))
 
 def forward(self, x):
 x = self.conv0(x)
 x = self.conv1(x)
 return x
 
class Net(nn.Module):
 def __init__(self, in_channels, mid_channels, out_channels):
 super(Net, self).__init__()
 self.conv0 = torch.nn.Sequential(
 torch.nn.Conv2d(in_channels, mid_channels, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
 torch.nn.LeakyReLU())
 self.conv1 = torch.nn.Sequential(
 torch.nn.Conv2d(mid_channels, out_channels * 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))
 
 def __call__(self, x):
 x = self.conv0(x)
 x = self.conv1(x)
 return x

from .modules import *
#nn.modules  导入modules目录下内容 定义容器modules
from .parameter import Parameter
#nn.Parameter 导入parameter.py  定义parameter
from .parallel import DataParallel
#导入parallel目录下data_parallel.py中的DataParallel类
from . import init
#nn.init   导入init.py   参数初始化
from . import utils
#nn.utils  导入utils目录下内容 官网api下nn.utils下api