# yolov11_cpp

**Repository Path**: SongpingWang/yolov11_cpp

## Basic Information

- **Project Name**: yolov11_cpp
- **Description**: yolov11_cpp
- **Primary Language**: C++
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2025-02-06
- **Last Updated**: 2025-04-28

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# yolov11_cpp

#### 介绍
yolov11_cpp


### cuda12.4.1包
```
https://developer.download.nvidia.cn/compute/cuda/12.4.1/local_installers/cuda_12.4.1_551.78_windows.exe
https://developer.nvidia.com/downloads/compute/cudnn/secure/8.8.1/local_installers/12.0/cudnn-windows-x86_64-8.8.1.3_cuda12-archive.zip/
```

### libtorch2.6.0-cpu包
```
https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-2.6.0%2Bcpu.zip
https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-debug-2.6.0%2Bcpu.zip
```

### libtorch2.6.0-gpu包
```
https://download.pytorch.org/libtorch/cu124/libtorch-win-shared-with-deps-2.6.0%2Bcu124.zip
https://download.pytorch.org/libtorch/cu124/libtorch-win-shared-with-deps-debug-2.6.0%2Bcu124.zip
```


### 预编译参数
```
_SILENCE_CXX17_RESULT_OF_DEPRECATION_WARNING
_SILENCE_CXX17_ADAPTOR_TYPEDEFS_DEPRECATION_WARNING
_SILENCE_CXX17_ITERATOR_BASE_CLASS_DEPRECATION_WARNING



opencv_core452d.lib
opencv_imgcodecs452d.lib
opencv_imgproc452d.lib
opencv_highgui452d.lib

asmjit.lib
c10.lib
cpuinfo.lib
dnnl.lib
fbgemm.lib
fmtd.lib
kineto.lib
libprotobuf-lited.lib
libprotobufd.lib
libprotocd.lib
pthreadpool.lib
sleef.lib
torch.lib
torch_cpu.lib
XNNPACK.lib
```

```cpp
#include <torch/script.h>
#include <iostream>
#include <memory>
#include <torch/torch.h>

int main() {
	auto device = torch::kCPU;
	// Deserialize the ScriptModule from a file using torch::jit::load().
	torch::jit::script::Module module = torch::jit::load(FileName, device);

	assert(module != nullptr);
	std::cout << "ok\n";
	// Create a vector of inputs.
	std::vector<torch::jit::IValue> inputs;
	inputs.push_back(torch::ones({ 1,3,320,192 }));

	// Execute the model and turn its output into a tensor.
	auto o = module.forward(std::move(inputs));
	at::Tensor output = o.toTensor();

	std::cout << output.slice(/*dim=*/1, /*start=*/0, /*end=*/5) << '\n';
	while (1);
}


```

### 大模型提问
```json
你好，你是个深度学习专家，熟练掌握 pytorch/python, libtorch/C++,其中pytorch/libtorch版本号为2.6.0

背景： 我需要将 pytorch/python的yolov11训练代码使用libtorch/C++进行实现
需求： 要求libtorch/C++实现时不能违背pytorch/python实现的主体功能，尽可能使用一样的方法函数，如libtorch/C++不存在类似的方法使用相近或者类似的方法，实在没有则自己实现，并详细说明。
需求： 要求libtorch/C++实现时不能违背pytorch/python实现的主体功能，尽可能使用一样的方法函数，如libtorch/C++不存在类似的方法使用相近或者类似的方法，实在没有则自己实现，并详细说明。



```