原标题:Pytorch构建ResNet
原文来自:博客园 原文链接:https://www.cnblogs.com/yqpy/p/11321926.html
学了几天Pytorch,大致明白代码在干什么了,贴一下。。
import torch
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision import transforms
from torch import nn, optim
from torch.nn import functional as F
class ResBlk(nn.Module):
"""
resnet block
"""
def __init__(self, ch_in, ch_out):
super(ResBlk, self).__init__()
self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1)
self.bn1 = nn.BatchNorm2d(ch_out)
self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
self.bn2 = nn.BatchNorm2d(ch_out)
self.extra = nn.Sequential()
if ch_out != ch_in:
# [b, ch_in, h, w] => [b, ch_out, h, w]
self.extra = nn.Sequential(
nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=1),
nn.BatchNorm2d(ch_out)
)
def forward(self,x):
"""
x:[b, ch, h, w]
"""
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
# short cut
# extra module: [b, ch_in, h, w] => [b, ch_out, h, w]
# element-wise add: [b, ch_in, h, w] with [b, ch_out, h, w]
out = self.extra(x) + out
return out
class ResNet18(nn.Module):
def __init(self):
super(ResNet18, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3,64,kernel_size=3, stride=1, padding=1),
nn.BatchNorm2d(64)
)
# followd 4 blocks
# [b, 64, h, w] => [b, 128, h, w]
self.blk1 = ResBlk(64,128)
# [b, 128, h, w] => [b, 256, h, w]
self.blk2 = ResBlk(128,256)
# [b, 256, h, w] => [b, 512, h, w]
self.blk3 = ResBlk(256,512)
# [b, 512, h, w] => [b, 1024, h, w]
self.blk4 = ResBlk(512,1024)
self.outlayer = nn.Linear(1024, 10)
def forward(self, x):
x = F.relu(self.conv1(x))
# [b, 64, h, w] => [b, 1024, h, w]
x = self.blk1(x)
x = self.blk2(x)
x = self.blk3(x)
x = self.blk4(x)
x = self.outlayer(x)
return x
def main():
blk = ResBlk(64, 128)
tmp = torch.randn(2, 64, 32, 32)
out = blk(tmp)
print(out.shape)
if __name__ == '__main__':
main()
#
torch.Size([2, 128, 32, 32])
ResNet主要是利用残差相加的优势进行网络层数加深,原来输入图片是64通道,要求经过一个ResNet Block后输出是128维,那么那个要加的X也要升维变成128,因此代码里做出了处理。
免责声明:本文来自互联网新闻客户端自媒体,不代表本网的观点和立场。
合作及投稿邮箱:E-mail:editor@tusaishared.com