Translate recipes_index

docs/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: ff98f6fae0a75c232c4a4aa789f50b6c
+config: 35f9c8212976e13237c532396976720c
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_sources/recipes/torchscript_inference.rst.txt

@@ -48,20 +48,20 @@ TorchScript 是使用 PyTorch 模型进行大规模推理的推荐模型格式
    r18_scripted = torch.jit.script(r18)         # *** 这是 TorchScript 导出
    dummy_input = torch.rand(1, 3, 224, 224)     # 快速测试一下
 
-Let’s do a sanity check on the equivalence of the two models:
+让我们快速检查一下两个模型的等价性:
 
 ::
 
-   unscripted_output = r18(dummy_input)         # Get the unscripted model's prediction...
-   scripted_output = r18_scripted(dummy_input)  # ...and do the same for the scripted version
+   unscripted_output = r18(dummy_input)         # 获取未脚本化模型的预测...
+   scripted_output = r18_scripted(dummy_input)  # ...并对脚本化版本做同样操作
 
    unscripted_top5 = F.softmax(unscripted_output, dim=1).topk(5).indices
    scripted_top5 = F.softmax(scripted_output, dim=1).topk(5).indices
 
    print('Python model top 5 results:\n  {}'.format(unscripted_top5))
    print('TorchScript model top 5 results:\n  {}'.format(scripted_top5))
 
-You should see that both versions of the model give the same results:
+会看到两个版本的模型给出相同的结果:
 
 ::
 
@@ -70,16 +70,17 @@ You should see that both versions of the model give the same results:
    TorchScript model top 5 results:
      tensor([[463, 600, 731, 899, 898]])
 
-With that check confirmed, go ahead and save the model:
+确认检查通过后,继续保存模型:
 
 ::
 
    r18_scripted.save('r18_scripted.pt')
 
 Loading TorchScript Models in C++
+在 C++ 中加载 TorchScript 模型
 ---------------------------------
 
-Create the following C++ file and name it ``ts-infer.cpp``:
+创建以下 C++ 文件,并将其命名为 ``ts-infer.cpp``:
 
 .. code:: cpp
 
@@ -95,7 +96,7 @@ Create the following C++ file and name it ``ts-infer.cpp``:
 
        std::cout << "Loading model...\n";
 
-       // deserialize ScriptModule
+       // 反序列化 ScriptModule
        torch::jit::script::Module module;
        try {
            module = torch::jit::load(argv[1]);
@@ -107,14 +108,14 @@ Create the following C++ file and name it ``ts-infer.cpp``:
 
        std::cout << "Model loaded successfully\n";
 
-       torch::NoGradGuard no_grad; // ensures that autograd is off
-       module.eval(); // turn off dropout and other training-time layers/functions
+       torch::NoGradGuard no_grad; // 确保自动梯度计算关闭
+       module.eval(); // 关闭 dropout 和其他训练时层/函数
 
-       // create an input "image"
+       // 创建一个输入"图像"
        std::vector<torch::jit::IValue> inputs;
        inputs.push_back(torch::rand({1, 3, 224, 224}));
 
-       // execute model and package output as tensor
+       // 执行模型并将输出打包为张量
        at::Tensor output = module.forward(inputs).toTensor();
 
        namespace F = torch::nn::functional;
@@ -128,20 +129,20 @@ Create the following C++ file and name it ``ts-infer.cpp``:
        return 0;
    }
 
-This program:
+程序步骤:
 
--  Loads the model you specify on the command line
-- Creates a dummy “image” input tensor
-- Performs inference on the input
+- 加载您在命令行上指定的模型
+- 创建一个虚拟的"图像"输入张量
+- 对输入执行推理
 
-Also, notice that there is no dependency on TorchVision in this code.
-The saved version of your TorchScript model has your learning weights
-*and* your computation graph - nothing else is needed.
+另外,请注意这段代码中没有依赖 TorchVision。
+保存的 TorchScript 模型包含您的学习权重和您的计算图。
 
-Building and Running Your C++ Inference Engine
+构建和运行您的 C++ 推理引擎
 ----------------------------------------------
 
-Create the following ``CMakeLists.txt`` file:
+创建以下 ``CMakeLists.txt`` 文件:
+
 
 ::
 
@@ -154,14 +155,14 @@ Create the following ``CMakeLists.txt`` file:
    target_link_libraries(ts-infer "${TORCH_LIBRARIES}")
    set_property(TARGET ts-infer PROPERTY CXX_STANDARD 11)
 
-Make the program:
+构建程序:
 
 ::
 
    cmake -DCMAKE_PREFIX_PATH=<path to your libtorch installation>
    make
 
-Now, we can run inference in C++, and verify that we get a result:
+现在,我们可以在 C++ 中运行推理,并验证我们得到结果:
 
 ::
 
@@ -177,18 +178,13 @@ Now, we can run inference in C++, and verify that we get a result:
 
    DONE
 
-Important Resources
+其他资源
 -------------------
 
--  `pytorch.org`_ for installation instructions, and more documentation
-   and tutorials.
--  `Introduction to TorchScript tutorial`_ for a deeper initial
-   exposition of TorchScript
--  `Full TorchScript documentation`_ for complete TorchScript language
-   and API reference
+-  `pytorch.org`_  查看安装说明和更多文档和教程。
+-  `TorchScript 入门教程`_ 对 TorchScript 进一步了解
+-  `TorchScript 文档`_ 查看完整的 TorchScript 语言和 API 参考
 
 .. _pytorch.org: https://pytorch.org/
-.. _Introduction to TorchScript tutorial: https://pytorch.org/tutorials/beginner/Intro_to_TorchScript_tutorial.html
-.. _Full TorchScript documentation: https://pytorch.org/docs/stable/jit.html
-.. _在 C++ 中加载 TorchScript 模型教程: https://pytorch.org/tutorials/advanced/cpp_export.html
-.. _full TorchScript documentation: https://pytorch.org/docs/stable/jit.html
+.. _TorchScript 入门教程: https://pytorch.org/tutorials/beginner/Intro_to_TorchScript_tutorial.html
+.. _TorchScript 文档: https://pytorch.org/docs/stable/jit.html