Rik*_*ika 1 c++ object-detection tensorflow object-detection-api
我们已经训练了我们的模型,并使用提供的Python脚本成功地测试了它们。但是,我们现在希望将其部署在我们的网站上并运行网络服务以进行第二轮测试。
是否有一个C ++包装器,以便我们可以像使用Python脚本一样使用它来运行/执行模型?
小智 5
I think the easiest way is to use cppflow. It is a C++ wrapper for the TensorFlow C API. It is simple but really easy to use and you do not need to install it neither compiling with Bazel. You just have to download the C API and use it like this:
Model model("graph.pb");
model.restore("path/to/checkpoint");
auto input = new Tensor(model, "input");
auto output = new Tensor(model, "output");
model.run(input, output);
Run Code Online (Sandbox Code Playgroud)
| 归档时间: |
|
| 查看次数: |
2543 次 |
| 最近记录: |