深度学习（十七）卷积神经网络残差网络RESNET 新手入门及常见问题解决

最新推荐文章于 2024-10-08 16:22:21 发布

浮云白日303

最新推荐文章于 2024-10-08 16:22:21 发布

阅读量378

点赞数 11

文章标签：深度学习 cnn 人工智能 python 学习神经网络机器学习

本文链接：https://blog.csdn.net/m0_68737530/article/details/136002097

版权

###Resnet

import torch
from torch import nn
from d2l import torch as d2l
from torch.nn import functional as f
###Resnet块
class resnet_yikuai(nn.Module):
  def __init__(self,input_channel,out_channel,use_conv1x1=False,buchang=1):
      super().__init__()
      self.conv1 = nn.Conv2d(input_channel,out_channel,kernel_size=3,padding=1,stride=buchang)
      self.conv2 = nn.Conv2d(out_channel,out_channel,kernel_size=3,padding=1)
      if use_conv1x1:
          self.conv3 = nn.Conv2d(input_channel,out_channel,kernel_size=1,stride=buchang)
      else:
          self.conv3 =None
      self.bh1 = nn.BatchNorm2d(out_channel)
      self.bh2 = nn.BatchNorm2d(out_channel)