libtorch 权重封装

网上demo，估计是版本问题不能用

https://github.com/LvJC/demo-libtorch

这个能封装，libtorch1.1可以调用，之前版本不能调用：

  

   

    

     

    
    

     

      import torch
     
    
   

    

     

    
    

     

      import torchvision
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      # An instance of your model.
     
    
   

    

     

    
    

     

      model = torchvision.models.resnet18()
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      # An example input you would normally provide to your model's forward() method.
     
    
   

    

     

    
    

     

      example = torch.rand(1, 3, 224, 224)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      # Use torch.jit.trace to generate a torch.jit.ScriptModule via tracing.
     
    
   

    

     

    
    

     

      traced_script_module = torch.jit.trace(model, example)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      traced_script_module.save("model.pt")
     
    
  
 

上面这个，torch1.0版本下报错：NameError: name 'false' is not defined

报错代码：self.bn1 = nn.BatchNorm2d(64)

c++调用：

  

   

    

     

    
    

     

      try
     
    
   

    

     

    
    

     

      	{
     
    
   

    

     

    
    

     

      		std::shared_ptr<torch::jit::script::Module> module = torch::jit::load("../mo
     
    
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/93326687