第五章：PyTorch模型定义

最新推荐文章于 2024-06-04 10:10:03 发布

DMS_Frank

最新推荐文章于 2024-06-04 10:10:03 发布

阅读量391

点赞数 1

文章标签： pytorch 深度学习 python

本文链接：https://blog.csdn.net/ladyfrank1113/article/details/126923659

版权

第五章:Pytorch模型的定义

import os
import numpy as np
import collections
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision

5.1 Pytorch模型的定义的方式

PyTorch中自定义模型主要通过以下三种方式：

Sequential
Ordered Dict
ModuleList
ModuleDict

5.1.2 Sequential

## Sequential: Direct list
import torch.nn as nn
net1 = nn.Sequential(
        nn.Linear(784, 256),
        nn.ReLU(),
        nn.Linear(256, 10), 
        )
print(net1)

Sequential(
  (0): Linear(in_features=784, out_features=256, bias=True)
  (1): ReLU()
  (2): Linear(in_features=256, out_features=10, bias=True)
)

## Sequential: Ordered Dict
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)
)


a = torch.rand(4,784)
out1 = net1(a)
out2 = net2(a)
print(out1.shape==out2.shape, out1.shape) #True表明这两个结构相同

True torch.Size([4, 10])

5.1.2 ModuleList

net3 = nn.ModuleList([nn.Linear(784, 256), nn.ReLU()])
net3.append(nn.Linear(256, 10)) # # 类似List的append操作
print(net3[-1])  # 类似List的索引访问
print(net3)

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)
)

# 注意ModuleList 并没有定义一个网络，它只是将不同的模块储存在一起。这样就不可以
out3 = net3(a)

---------------------------------------------------------------------------

NotImplementedError                       Traceback (most recent call last)

<ipython-input-6-0abc9bfebdbc> in <module>
      1 # 注意ModuleList 并没有定义一个网络，它只是将不同的模块储存在一起。此处应报错
----> 2 out3 = net3(a)


/data1/ljq/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
   1100         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1101                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1102             return forward_call(*input, **kwargs)
   1103         # Do not call functions when jit is used
   1104         full_backward_hooks, non_full_backward_hooks = [], []


/data1/ljq/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _forward_unimplemented(self, *input)
    199         registered hooks while the latter silently ignores them.
    200     """
--> 201     raise NotImplementedError
    202 
    203 


NotImplementedError:

class Net3(nn.Module):
    def __init__(self):
        super().__init__()
        self.modulelist = nn.ModuleList([nn.Linear(784, 256), nn.ReLU()])
        self.modulelist.append(nn.Linear(256, 10))
    
    def forward(self, x):
        for layer in self.modulelist:
            x = layer(x)
        return x
net3_ = Net3()
out3_ = net3_(a)
print(out3_.shape)

torch.Size([4, 10])

5.1.3 ModuleDict

net4 = nn.ModuleDict({
    'linear': nn.Linear(784, 256),
    'act': nn.ReLU(),
})
net4['output'] = nn.Linear(256, 10) # 添加
print(net4['linear']) # 访问
print(net4.output)

Linear(in_features=784, out_features=256, bias=True)
Linear(in_features=256, out_features=10, bias=True)

# 同样地，ModuleDict并没有定义一个网络，它只是将不同的模块储存在一起。此处应报错。
# 正确使用方式同上
out4 = net4(a)

---------------------------------------------------------------------------

NotImplementedError                       Traceback (most recent call last)

<ipython-input-11-965aa5709079> in <module>
      1 # 同样地，ModuleDict并没有定义一个网络，它只是将不同的模块储存在一起。此处应报错。
      2 # 正确使用方式同上
----> 3 out4 = net4(a)


/data1/ljq/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
   1100         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1101                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1102             return forward_call(*input, **kwargs)
   1103         # Do not call functions when jit is used
   1104         full_backward_hooks, non_full_backward_hooks = [], []


/data1/ljq/anaconda3/lib/python3.8/site-packages/torch/nn/modules/module.py in _forward_unimplemented(self, *input)
    199         registered hooks while the latter silently ignores them.
    200     """
--> 201     raise NotImplementedError
    202 
    203 


NotImplementedError:

5.2 利用模型块快速搭建复杂网络

下面我们开始探索如何利用模型块，快速构建U-Net网络
[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-1AuGSaJJ-1663508284304)(./unet.png)]
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

除模型块外，还有模型块之间的横向连接，输入和U-Net底部的连接等计算，这些单独的操作可以通过forward函数来实现。
（参考：https://github.com/milesial/Pytorch-UNet ）

import os
import numpy as np
import collections
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision

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 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)

## 组装
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

unet = UNet(3,1)
unet

UNet(
  (inc): DoubleConv(
    (double_conv): Sequential(
      (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
      (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): ReLU(inplace=True)
    )
  )
  (down1): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down2): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down3): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down4): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (up1): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up2): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up3): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up4): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (outc): OutConv(
    (conv): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
  )
)

5.3 pytorch模型修改

这里我们假设最后的分割是多类别的（即mask不止0和1，还有2，3，4等值代表其他目标），需要对模型特定层进行修改。
此外还有两种情况的模型修改方式，这里也做演示：

添加额外输入
添加额外输出

5.3.1 修改特定层

import copy
unet1 = copy.deepcopy(unet)
unet1.outc

OutConv(
  (conv): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
)

b = torch.rand(1,3,224,224)
out_unet1 = unet1(b)
print(out_unet1.shape)

torch.Size([1, 1, 224, 224])

unet1.outc = OutConv(64, 5)
unet1.outc

OutConv(
  (conv): Conv2d(64, 5, kernel_size=(1, 1), stride=(1, 1))
)

out_unet1 = unet1(b)
print(out_unet1.shape)

torch.Size([1, 5, 224, 224])

5.3.2 添加额外输入

class UNet2(nn.Module):
    def __init__(self, n_channels, n_classes, bilinear=True):
        super(UNet2, 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, add_variable):
        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)
        x = x + add_variable   #修改点
        logits = self.outc(x)
        return logits
unet2 = UNet2(3,1)

c = torch.rand(1,1,224,224)
out_unet2 = unet2(b, c)
print(out_unet2.shape)

torch.Size([1, 1, 224, 224])

5.3.2添加额外输出

class UNet3(nn.Module):
    def __init__(self, n_channels, n_classes, bilinear=True):
        super(UNet3, 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, x5  # 修改点
unet3 = UNet3(3,1)

c = torch.rand(1,1,224,224)
out_unet3, mid_out = unet3(b)
print(out_unet3.shape, mid_out.shape)

torch.Size([1, 1, 224, 224]) torch.Size([1, 512, 14, 14])

5.4 模型保存与读取

这里相应考虑单卡和多卡情况下的模型存取情况

## 讲解点：回到jupyter的文件目录下，看保存的结果

两种训练模式：
1.CPU或单卡
2.多卡并行的情况

两种保存类型：
1.保存整个模型
2.保存模型权重。

UNet(
  (inc): DoubleConv(
    (double_conv): Sequential(
      (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (2): ReLU(inplace=True)
      (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (5): ReLU(inplace=True)
    )
  )
  (down1): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down2): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down3): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (down4): Down(
    (maxpool_conv): Sequential(
      (0): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
      (1): DoubleConv(
        (double_conv): Sequential(
          (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (2): ReLU(inplace=True)
          (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
          (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
          (5): ReLU(inplace=True)
        )
      )
    )
  )
  (up1): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(1024, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up2): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(512, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up3): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(256, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (up4): Up(
    (up): Upsample(scale_factor=2.0, mode=bilinear)
    (conv): DoubleConv(
      (double_conv): Sequential(
        (0): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (2): ReLU(inplace=True)
        (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
        (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
        (5): ReLU(inplace=True)
      )
    )
  )
  (outc): OutConv(
    (conv): Conv2d(64, 1, kernel_size=(1, 1), stride=(1, 1))
  )
)

5.4.1 模型的保存格式

1.pt、
2.pth、
3.pkl、

unet.state_dict()

5.4.2 单卡与多卡模型存储的区别

CPU或单卡：保存&读取整个模型
torch.save(unet, “./unet_example.pth”)
loaded_unet = torch.load(“./unet_example.pth”)
loaded_unet.state_dict()

CPU或单卡：保存&读取模型权重
torch.save(unet.state_dict(), “./unet_weight_example.pth”)
loaded_unet_weights = torch.load(“./unet_weight_example.pth”)
unet.load_state_dict(loaded_unet_weights)
unet.state_dict()

多卡：保存&读取整个模型。注意模型层名称前多了module
不建议，因为保存模型的GPU_id等信息和读取后训练环境可能不同，尤其是要把保存的模型交给另一用户使用的情况
os.environ[‘CUDA_VISIBLE_DEVICES’] = ‘2,3’
unet_mul = copy.deepcopy(unet)
unet_mul = nn.DataParallel(unet_mul).cuda()
unet_mul

torch.save(unet_mul, “./unet_mul_example.pth”)
loaded_unet_mul = torch.load(“./unet_mul_example.pth”)
loaded_unet_mul

多卡：保存&读取模型权重。
torch.save(unet_mul.state_dict(), “./unet_weight_mul_example.pth”)
loaded_unet_weights_mul = torch.load(“./unet_weight_mul_example.pth”)
unet_mul.load_state_dict(loaded_unet_weights_mul)
unet_mul = nn.DataParallel(unet_mul).cuda()
unet_mul.state_dict()

另外，如果保存的是整个模型，也建议采用提取权重的方式构建新的模型：
unet_mul.state_dict = loaded_unet_mul.state_dict
unet_mul = nn.DataParallel(unet_mul).cuda()
unet_mul.state_dict()