学习目标:
PyTorch模型定义
1.1PyTorch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),是所有神经⽹网络模块的基类,我们可以继承它来定义我们想要的模型;
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。
from collections import OrderedDict
import torch.nn as nn
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self._modules(一个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
import torch.nn as nn
net = nn.Sequential(
nn.Linear(784, 256),
nn.ReLU(),
nn.Linear(256, 10),
)
print(net)
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)
net = nn.ModuleList([nn.Linear(784, 256), nn.ReLU()])
net.append(nn.Linear(256, 10)) # # 类似List的append操作
print(net[-1]) # 类似List的索引访问
print(net)
net = nn.ModuleDict({
'linear': nn.Linear(784, 256),
'act': nn.ReLU(),
})
net['output'] = nn.Linear(256, 10) # 添加
print(net['linear']) # 访问
print(net.output)
print(net)
1.2 利用模型块快速搭建复杂网络
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])
# if you have padding issues, see
# https://github.com/HaiyongJiang/U-Net-Pytorch-Unstructured-Buggy/commit/0e854509c2cea854e247a9c615f175f76fbb2e3a
# https://github.com/xiaopeng-liao/Pytorch-UNet/commit/8ebac70e633bac59fc22bb5195e513d5832fb3bd
x = torch.cat([x2, x1], dim=1)
return self.conv(x)
class UNet:
pass
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)
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
1.3 PyTorch修改模型
from collections import OrderedDict
classifier = nn.Sequential(OrderedDict([('fc1', nn.Linear(2048, 128)),
('relu1', nn.ReLU()),
('dropout1', nn.Dropout(0.5)),
('fc2', nn.Linear(128, 10)),
('output', nn.Softmax(dim=1))
]))
net.fc = classifier
class Model(nn.Module):
def __init__(self, net):
super(Model, self).__init__()
self.net = net
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
self.fc_add = nn.Linear(1001, 10, bias=True)
self.output = nn.Softmax(dim=1)
def forward(self, x, add_variable):
x = self.net(x)
x = torch.cat((self.dropout(self.relu(x)), add_variable.unsqueeze(1)), 1)
x = self.fc_add(x)
x = self.output(x)
return x
import torchvision.models as models
net = models.resnet50()
model = Model(net).cuda()
outputs = model(inputs, add_var)
class Model(nn.Module):
def __init__(self, net):
super(Model, self).__init__()
self.net = net
self.relu = nn.ReLU()
self.dropout = nn.Dropout(0.5)
self.fc1 = nn.Linear(1000, 10, bias=True)
self.output = nn.Softmax(dim=1)
def forward(self, x, add_variable):
x1000 = self.net(x)
x10 = self.dropout(self.relu(x1000))
x10 = self.fc1(x10)
x10 = self.output(x10)
return x10, x1000
import torchvision.models as models
net = models.resnet50()
model = Model(net).cuda()
out10, out1000 = model(inputs, add_var)
from torchvision import models
model = models.resnet152(pretrained=True)
# 保存整个模型
torch.save(model, save_dir)
# 保存模型权重
torch.save(model.state_dict, save_dir)
os.environ['CUDA_VISIBLE_DEVICES'] = '0' # 如果是多卡改成类似0,1,2
model = model.cuda() # 单卡
model = torch.nn.DataParallel(model).cuda() # 多卡
1.4 PyTorch模型保存与读取
学习内容:
学习时间:
2小时
学习产出:
`