【Pytorch】网络模型的保存和读取 - 学习笔记

视频地址

保存与读取方式1

保存方式1读取方式1方式1的陷阱 保存与读取方式2

保存方式2读取方式2

import torch
import torchvision

vgg16 = torchvision.models.vgg16(pretrained=False)
# 保存方式1 后缀最好是.pth，可以同时保存模型及参数
torch.save(vgg16, "vgg16_method1.pth")

import torch
import torchvision

# 方式1->保存方式1，加载模型
model = torch.load("vgg16_method1.pth")

print(model)

运行结果为

D:Anaconda3envspytorchpython.exe D:/研究生/代码尝试/model_load.py
VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace=True)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace=True)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace=True)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace=True)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace=True)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace=True)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace=True)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace=True)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace=True)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace=True)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace=True)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace=True)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace=True)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (avgpool): AdaptiveAvgPool2d(output_size=(7, 7))
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace=True)
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace=True)
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)

Process finished with exit code 0

当创建自己的网络时，如果在两个文件里保存和读取，那么读取的时候会报错，需要把模型的类复制到读取的文件中

import torch
import torchvision

vgg16 = torchvision.models.vgg16(pretrained=False)

# 保存方式2，把vgg16的状态（参数）保存为字典，没有结构 【官方推荐】因为空间小
torch.save(vgg16.state_dict(), "vgg16_method2.pth")

import torch
import torchvision

# 方式2，加载模型
model = torch.load("vgg16_method2.pth")
print(model)

输出结果为字典形式（比较长，截取了一部分）

OrderedDict([('features.0.weight', tensor([[[[ 0.0203,  0.0550, -0.0628],
          [-0.0034,  0.0760,  0.0692],
          [-0.1093,  0.0214, -0.0057]],

         [[-0.0381, -0.1053, -0.0022],
          [-0.0064,  0.0445, -0.0055],
          [ 0.0248, -0.0268, -0.0438]],

         [[-0.0004,  0.0012,  0.0095],
          [-0.0862, -0.1330, -0.0214],
          [ 0.0617, -0.0075, -0.0484]]],
          ...

如果我们想要把模型结构也加载出来呢？

import torch

# 方式2，加载模型
vgg16 = torchvision.models.vgg16(pretrained=False)
# 参数和结构放一起
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
# model = torch.load("vgg16_method2.pth")
print(vgg16)