哔哩大学的PyTorch深度学习快速入门教程(绝对通俗易懂!)【小土堆】
的P26讲讲述了如何保存与读取网络模型.
保存代码:
import torch
import torchvision
from torch import nn
vgg16 = torchvision.models.vgg16(pretrained=False)
# 保存方式1 “保存路径.pth”什么后缀都行推荐为.pth 保存了结构和参数pip
torch.save(vgg16, "vgg16_method1.pth")
# 保存方式2 , 模型参数(官方推荐)
torch.save(vgg16.state_dict(), "vgg16_method2.pth")
# 陷阱
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=3)
def forward(self, x):
x = self.conv1(x)
return x
tudui = Tudui()
torch.save(tudui, "tudui_method1.pth")
效果:
图中tudui_method1.pth即为代码中的tudui模型:
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.conv1 = nn.Conv2d(3, 64, kernel_size=3)
def forward(self, x):
x = self.conv1(x)
return x
读取代码为:
import torch
from model_save import *
import torchvision
model = torch.load("vgg16_method1.pth")
vgg16 = torchvision.models.vgg16(pretrained=False)
vgg16.load_state_dict(torch.load("vgg16_method2.pth"))
model = torch.load('tudui_method1.pth')
print(model)
运行结果为上边写的tudui_method1.pth