LibTorch模型无法常驻CUDA设备问题求助

无法将模型放置并常驻在CUDA设备上。当传入已在CUDA上的张量时，会触发**"found at least two devices, cpu and cuda"**错误。

我是否遗漏了在LibTorch中将模型部署到CUDA设备的简单方法？找不到解决方案。

核心问题代码示例 #

当张量已在CUDA上时，传入模型会报错：

auto the_tensor = torch::rand({42, 427}).to(device);
std::cout << net.forward(the_tensor).to(device);  

terminate called after throwing an instance of 'c10::Error'
what():  Expected all tensors to be on the same device, but found at least two devices, cpu and 
cuda:0! (when checking argument for argument mat1 in method wrapper_addmm)

若张量不在CUDA上，可正常在CUDA运行模型：

auto the_tensor = torch::rand({42, 427});
std::cout << net.forward(the_tensor).to(device);  

将张量转回CPU也不会报错，但我的脚本中有大量已在CUDA上的张量，不想来回转移，因此寻求将模型永久部署在CUDA设备的方法。

尝试过的无效方法 #

net.to(device);
net->to(device);
Critic_Net().to(device);

只有在forward调用后添加.to(device)才能正常运行，以下是完整可复现代码：

#include <torch/torch.h>
using namespace torch::indexing;

torch::Device device(torch::kCUDA);

struct Critic_Net : torch::nn::Module {
    torch::Tensor next_state_batch__sampled_action;
    public:
    Critic_Net() {
        lin1 = torch::nn::Linear(427, 42);
        lin2 = torch::nn::Linear(42, 286);
        lin3 = torch::nn::Linear(286, 1);
    }
    torch::Tensor forward(torch::Tensor next_state_batch__sampled_action) {
        auto h = next_state_batch__sampled_action;
        h = torch::relu(lin1->forward(h));
        h = torch::tanh(lin2->forward(h));
        h = lin3->forward(h);
        return torch::nan_to_num(h);
    }
    torch::nn::Linear lin1{nullptr}, lin2{nullptr}, lin3{nullptr};
};

auto net = Critic_Net();


int main() {
    net.to(device);
    auto the_tensor = torch::rand({42, 427}).to(device);
    
    std::cout << net.forward(the_tensor).to(device);
}

内容的提问来源于stack exchange，提问作者Ant