# How to properly integrate Libtorch (Pytorch) and Unreal Engine 4?

**URL:** <https://forums.unrealengine.com/t/how-to-properly-integrate-libtorch-pytorch-and-unreal-engine-4/263158>\
**Category:** AI\
**Tags:** unreal-engine\
**Created:** [November 29, 2021, 4:13am UTC](https://forums.unrealengine.com/t/how-to-properly-integrate-libtorch-pytorch-and-unreal-engine-4/263158 "2021-11-29T04:13:50Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Amethystium77](https://d3kjluh73b9h9o.cloudfront.net/original/4X/2/8/5/28502927f1d97ba1051b3b47ccfe17233bf41ef0.png) [@Amethystium77](https://forums.unrealengine.com/u/Amethystium77)\
**Post date:** [November 29, 2021, 4:13am UTC](https://forums.unrealengine.com/t/how-to-properly-integrate-libtorch-pytorch-and-unreal-engine-4/263158/1 "2021-11-29T04:13:50Z")

</div>

Visual Studio 2019  
Unreal Engine 4 (4.26.2)  
Libtorch 1.10 versión CPU release mode

When I integrate Libtorch (Pytorch) into Visual studio 2019 in release mode. I can run my algorithms without problems.

However, when I integrate Libtorch into Unreal Engine 4 in Debelopment Editor mode I get an error in runtime in the funtion at :: Tensor output = module.forward (inputs) .toTensor ();

I have tried for a couple of weeks to resolve the error at runtime, but I have not succeeded.

Please, could someone give me any suggestions?

* * *

In order to replicate the error:

- Create a new Project in PyCharm
- Install PyTorch: pip3 install torch torchvision torchaudio  
-Write the following code:

```auto
 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("D:\\resnet18.pt")

```

-Download Libtorch: Stable (1.10), Windows, LibTorch, C++/Java and CPU (release mode).  
[https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-1.10.0%2Bcpu.zip](https://download.pytorch.org/libtorch/cpu/libtorch-win-shared-with-deps-1.10.0%2Bcpu.zip)

-Extract the zip in your PATH.

-Create a project in Unreal Engine 4 named MyProject of type ThirdPerson and of type C++ (the default project is in mode Development Editor).

-Close the editor of UE4

-Open the properties in Project → MyProject Properties. Select the configuration Development\_Editor and VC++ Directories.

- Add the paths in External Include Directories:  
(PATH)\libtorch-win-shared-with-deps-1.10.0+cpu\libtorch\include  
(PATH)\libtorch-win-shared-with-deps-1.10.0+cpu\libtorch\include\torch\csrc\api\include

- Add the library int Library Directories:  
(PATH)\libtorch-win-shared-with-deps-1.10.0+cpu\libtorch\lib

- Add PublicAdditionalLibraries int the MyProject.Build.cs:

```auto
public class MyProject : ModuleRules
{
	public MyProject(ReadOnlyTargetRules Target) : base(Target)
	{
		PCHUsage = PCHUsageMode.UseExplicitOrSharedPCHs;
		PublicDependencyModuleNames.AddRange(new string[] { "Core", "CoreUObject", "Engine", "InputCore", "HeadMountedDisplay" });
		PublicAdditionalLibraries.Add("(PATH)\\libtorch-win-shared-with-deps-1.10.0+cpu\\libtorch\\lib\\torch_cpu.lib");
		PublicAdditionalLibraries.Add("(PATH)\\libtorch-win-shared-with-deps-1.10.0+cpu\\libtorch\\lib\\c10.lib");
		PublicAdditionalLibraries.Add("(PATH)\\libtorch-win-shared-with-deps-1.10.0+cpu\\libtorch\\lib\\torch.lib");
	}
}

```

- Paste the dynamic libraries (dlls) in the Win64 directory of the UE4 project: (PATH)\MyProject\Binaries\Win64  
Librarys: asmjit.dll, c10.dll. fbgemm.dll, libiomp5md.dll, libiompstubs5md.dll, torch.dll, torch\_cpu.dll and uv.dll

- Paste on the top of file MyProjectCharacter.h: #include \<torch/script.h\>. If you Build the project you get a lot of notes, warnings and errors.

- Replace :#include \<torch/script.h\> with:

```auto
#pragma warning( push )
#pragma warning(disable: 4582)
#pragma warning(disable: 4583)
#pragma warning(disable: 4458)
#pragma warning(disable: 4624)
#pragma warning(disable: 4800)
#pragma warning(disable: 4541)
#include <torch/script.h> // One-stop header.
#pragma warning( pop )

```

- Add the follow code in the constructor of your MyProjectCharacter.cpp

```auto
torch::device(torch::kCPU);
torch::jit::script::Module module = torch::jit::load("D:\\resnet18.pt");
assert(module != nullptr);
std::cout << "ok\n";

```

- Build the project, everything should run fine.

- Add the following code after the code above:

```auto
// Create a vector of inputs.
std::vector<torch::jit::IValue> inputs;
inputs.push_back(torch::ones({1, 3, 224, 224}));

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

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

```

- Select Debug  Options and uncheck: Use the new Exception Helper

- Build and Run, then, you get an error in runt time in: at::Tensor output = module.forward(inputs).toTensor();

- If you continue you get a new runtime error:  
Unhandled exception at 0x00007FFE8618F199 (ntdll.dll) in UE4Editor.exe: 0xC0000374: A heap has been corrupted (parameters: 0x00007FFE861F77F0).

 ![03](https://d3kjluh73b9h9o.cloudfront.net/original/3X/0/5/05fbaad89a854d4907759042abfccab27d3544ca.jpeg)

-If you continue your project your project will run normally. (for example: [Question Answering: BERT(Bidirectional Encoder Representation with Transformers) with LibTorch & UE4 - YouTube](https://www.youtube.com/watch?v=RqELfDc8Rqc))

- I have tried for a couple of weeks to resolve the error at runtime (for example, disabling optimization with #pragma optimize ("", off)), but I have not succeeded. The error in the heap continues.

---

<div class="post-metadata">

**Author:** ![lvoos](https://d3kjluh73b9h9o.cloudfront.net/original/4X/2/8/5/28502927f1d97ba1051b3b47ccfe17233bf41ef0.png) [@lvoos](https://forums.unrealengine.com/u/lvoos)\
**Post date:** [April 8, 2024, 2:15pm UTC](https://forums.unrealengine.com/t/how-to-properly-integrate-libtorch-pytorch-and-unreal-engine-4/263158/2 "2024-04-08T14:15:22Z")

</div>

Did you find a solution for this?  
You wrote “If you continue your project your project will run normally”.  
Hasn’t the runtime error affected your app’s lifecycle?

---

<div class="post-metadata">

**Author:** ![handdown](https://d3kjluh73b9h9o.cloudfront.net/original/4X/2/8/5/28502927f1d97ba1051b3b47ccfe17233bf41ef0.png) [@handdown](https://forums.unrealengine.com/u/handdown)\
**Post date:** [February 5, 2025, 9:14am UTC](https://forums.unrealengine.com/t/how-to-properly-integrate-libtorch-pytorch-and-unreal-engine-4/263158/3 "2025-02-05T09:14:17Z")

</div>

Did you find a solution for this? It doesnt affect work,but alway get an error for the first time。