Comments (7)
it might be pretty hard... #1083
from torchsharp.
but there must be a way as we know that c# is not capable enough to do much things like torch
from torchsharp.
make an easy and seamless integration.you may use pytorch mobile
from torchsharp.
You're not supposed to put torchlib on user devices, its too massive. You pretty much have two options:
- Export your models as ONNX and use that for inference.
- Build Asp .net core server application hosting TorchSharp stuff and expose it to android/ios frontend.
from torchsharp.
You're not supposed to put torchlib on user devices, its too massive. You pretty much have two options:
- Export your models as ONNX and use that for inference.
- Build Asp .net core server application hosting TorchSharp stuff and expose it to android/ios frontend.
but how does onnx exist for embedded devices?
from torchsharp.
You're not supposed to put torchlib on user devices, its too massive. You pretty much have two options:
- Export your models as ONNX and use that for inference.
- Build Asp .net core server application hosting TorchSharp stuff and expose it to android/ios frontend.
but how does onnx exist for embedded devices?
Something exists. For instance Unity already made two ONNX inference engines that run on mobile. The recent one is called Sentis, you can maybe use that? https://unity.com/products/sentis
from torchsharp.
TorchSharp supports the platforms that libtorch supports: the CPU backend on Windows X64, MacOS M1/M2/M3, Linux X64. In addition, both Windows and Linux support then libtorch CUDA backends.
from torchsharp.
Related Issues (20)
- Linear module creates parameter on cpu even after I set default device to meta HOT 1
- Request tensor factory methods accepting Span<T> HOT 9
- The function torch.cuda.empty_cache() is missing. HOT 6
- Move to libtorch 2.4.0 HOT 1
- Unexpected parameters HOT 11
- MultivariateNormal.log_prob() exception in TorchSharp but works in pytorch HOT 16
- Builds fail after package validation PR merged HOT 2
- Modernize torchsharp infrastructure
- Jagged Array to Tensor HOT 5
- Arrays of Arrays HOT 4
- IterableDataset
- Build failing after merge of PR 1354
- Suppress the API breakchange introduced by PR 1354 and bump up minor version HOT 3
- `torch.nn.functional.l1_loss` computes a criterion with the MSE, not the MAE HOT 6
- MissingMethodException: Method not found: '!!0 TorchSharp.ModuleExtensionMethods.cuda(!!0, Int32)' HOT 8
- Why this dotnet pack error?
- GELU does not appear to support approximate tanh HOT 4
- multi-gpu training HOT 2
- Using TorchSharp In Unity HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from torchsharp.