PyTorch模型定义的方式
Module 类是 torch.nn 模块里提供的一个模型构造类 (nn.Module),PyTorch模型定义应包括两个主要部分:各个部分的初始化(_init_);数据流向定义(forward)
基于nn.Module,我们可以通过Sequential,ModuleList和ModuleDict三种方式定义PyTorch模型。
Sequential
对应模块为nn.Sequential()
Sequential 类可以通过简单的方式定义模型,它接收一个子模块的有序字典(OrderedDict) 或者一系列子模块作为参数来逐一添加 Module 的实例,⽽模型的前向计算就是将这些实例按添加的顺序逐⼀计算。
class MySequential(nn.Module):
from collections import OrderedDict
def __init__(self, *args):
super(MySequential, self).__init__()
if len(args) == 1 and isinstance(args[0], OrderedDict): # 如果传入的是一个OrderedDict
for key, module in args[0].items():
self.add_module(key, module) # add_module方法会将module添加进OrderedDict
else: # 传入的是一些Module
for idx, module in enumerate(args):
self.add_module(str(idx), module)
def forward(self, input):
# self._modules返回一个 OrderedDict,保证会按照成员添加时的顺序遍历成
for module in self._modules.values():
input = module(input)
return input
Sequential定义模型:只需要将层按序列排列起来即可,根据层名的不同分为:
直接排列
import torch.nn as nn net = nn.Sequential( nn.Linear(784, 256), nn.ReLU(), nn.Linear(256, 10), ) print(net)Sequential( (0): Linear(in_features=784, out_features=256, bias=True) (1): ReLU() (2): Linear(in_features=256, out_features=10, bias=True) )
使用OrderedDict
import collections import torch.nn as nn net2 = nn.Sequential(collections.OrderedDict([ ('fc1', nn.Linear(784, 256)), ('relu1', nn.ReLU()), ('fc2', nn.Linear(256, 10)) ])) print(net2)Sequential( (fc1): Linear(in_features=784, out_features=256, bias=True) (relu1): ReLU() (fc2): Linear(in_features=256, out_features=10, bias=True) )
Sequential优点:
简单、易读,同时使用Sequential定义的模型不需要再写forward,因为顺序已经定义好了。
但使用Sequential也会使得模型定义丧失灵活性
ModuleList
对应模块为nn.ModuleList()
ModuleList 接收一个子模块或层(nn.Module类)的列表作为输入,可以进行append和extend操作,子模块或层的权重也会自动添加到网络中来。
net = nn.ModuleList([nn.Linear(784, 256), nn.ReLU()]) # nn.module作为输入 net.append(nn.Linear(256, 10)) # append操作 print(net[-1]) # 索引访问 print(net)Linear(in_features=256, out_features=10, bias=True) ModuleList( (0): Linear(in_features=784, out_features=256, bias=True) (1): ReLU() (2): Linear(in_features=256, out_features=10, bias=True) )
nn.ModuleList 并没有定义一个网络,它只是将不同的模块储存在一起。ModuleList中元素的先后顺序并不代表其在网络中的真实位置顺序,需要经过forward函数指定各个层的先后顺序后才算完成了模型的定义。
class model(nn.Module):
def __init__(self, ...):
super().__init__()
self.modulelist = [... , ...]
def forward(self, x):
for layer in self.modulelist:
x = layer(x)
return x
ModuleDict
对应模块为nn.ModuleDict()
ModuleDict很方便地为神经网络的层添加名称
net = nn.ModuleDict({ 'linear': nn.Linear(784, 256), 'act': nn.ReLU(), }) net['output'] = nn.Linear(256, 10) # 像ModuleList的append函数 print(net['linear']) # 访问中间层 print(net.output) print(net)Linear(in_features=784, out_features=256, bias=True) Linear(in_features=256, out_features=10, bias=True) ModuleDict( (act): ReLU() (linear): Linear(in_features=784, out_features=256, bias=True) (output): Linear(in_features=256, out_features=10, bias=True) )
三种方法适用的场景
Sequential适用于快速验证结果,因为已经明确了要用哪些层,直接写一下就好了,不需要同时写__init__和forward;ModuleList和ModuleDict在某个完全相同的层需要重复出现多次时,非常方便实现;当我们需要之前层的信息的时候,比如 ResNets 中的残差计算,当前层的结果需要和之前层中的结果进行融合,一般使用 ModuleList/ModuleDict 比较方便。
利用模型块快速搭建复杂网络
U-Net
组成U-Net的模型块主要有如下几个部分:
1)每个子块内部的两次卷积(Double Convolution)
2)左侧模型块之间的下采样连接,即最大池化(Max pooling)
3)右侧模型块之间的上采样连接(Up sampling)
4)输出层的处理
U-Net模型块实现
import torch
import torch.nn as nn
import torch.nn.functional as F
class DoubleConv(nn.Module):
"""(convolution => [BN] => ReLU) * 2"""
def __init__(self, in_channels, out_channels, mid_channels=None):
super().__init__()
if not mid_channels:
mid_channels = out_channels
self.double_conv = nn.Sequential(
nn.Conv2d(in_channels, mid_channels, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(mid_channels),
nn.ReLU(inplace=True),
nn.Conv2d(mid_channels, out_channels, kernel_size=3, padding=1, bias=False),
nn.BatchNorm2d(out_channels),
nn.ReLU(inplace=True)
)
def forward(self, x):
return self.double_conv(x)
class Down(nn.Module):
"""Downscaling with maxpool then double conv"""
def __init__(self, in_channels, out_channels):
super().__init__()
self.maxpool_conv = nn.Sequential(
nn.MaxPool2d(2),
DoubleConv(in_channels, out_channels)
)
def forward(self, x):
return self.maxpool_conv(x)
class Up(nn.Module):
"""Upscaling then double conv"""
def __init__(self, in_channels, out_channels, bilinear=True):
super().__init__()
# if bilinear, use the normal convolutions to reduce the number of channels
if bilinear:
self.up = nn.Upsample(scale_factor=2, mode='bilinear', align_corners=True)
self.conv = DoubleConv(in_channels, out_channels, in_channels // 2)
else:
self.up = nn.ConvTranspose2d(in_channels, in_channels // 2, kernel_size=2, stride=2)
self.conv = DoubleConv(in_channels, out_channels)
def forward(self, x1, x2):
x1 = self.up(x1)
# input is CHW
diffY = x2.size()[2] - x1.size()[2]
diffX = x2.size()[3] - x1.size()[3]
x1 = F.pad(x1, [diffX // 2, diffX - diffX // 2,
diffY // 2, diffY - diffY // 2])
x = torch.cat([x2, x1], dim=1)
return self.conv(x)
class OutConv(nn.Module):
def __init__(self, in_channels, out_channels):
super(OutConv, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=1)
def forward(self, x):
return self.conv(x)
利用模型块组装U-Net
使用利用模型块组装U-Net写好的模型块,可以非常方便地组装U-Net模型。可以看到,通过模型块的方式实现了代码复用,整个模型结构定义所需的代码总行数明显减少,代码可读性也得到了提升。
class UNet(nn.Module):
def __init__(self, n_channels, n_classes, bilinear=True):
super(UNet, self).__init__()
self.n_channels = n_channels
self.n_classes = n_classes
self.bilinear = bilinear
self.inc = DoubleConv(n_channels, 64)
self.down1 = Down(64, 128)
self.down2 = Down(128, 256)
self.down3 = Down(256, 512)
factor = 2 if bilinear else 1
self.down4 = Down(512, 1024 // factor)
self.up1 = Up(1024, 512 // factor, bilinear)
self.up2 = Up(512, 256 // factor, bilinear)
self.up3 = Up(256, 128 // factor, bilinear)
self.up4 = Up(128, 64, bilinear)
self.outc = OutConv(64, n_classes)
def forward(self, x):
x1 = self.inc(x)
x2 = self.down1(x1)
x3 = self.down2(x2)
x4 = self.down3(x3)
x5 = self.down4(x4)
x = self.up1(x5, x4)
x = self.up2(x, x3)
x = self.up3(x, x2)
x = self.up4(x, x1)
logits = self.outc(x)
return logits