TorchSharp.Fun 0.77.0

.NET 7.0 
dotnet add package TorchSharp.Fun --version 0.77.0
NuGet\Install-Package TorchSharp.Fun -Version 0.77.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="TorchSharp.Fun" Version="0.77.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add TorchSharp.Fun --version 0.77.0
#r "nuget: TorchSharp.Fun, 0.77.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
// Install TorchSharp.Fun as a Cake Addin
#addin nuget:?package=TorchSharp.Fun&version=0.77.0

// Install TorchSharp.Fun as a Cake Tool
#tool nuget:?package=TorchSharp.Fun&version=0.77.0

TorchSharp.Fun

A wrapper over TorchSharp that provides a function-compostion style of model construction. Makes the model structure more apparent. It is easier to make incremental changes to the model. Makes iterative model development faster.

Example usage

let lisht() = 
    F [] [] (fun z ->
        use g = torch.nn.functional.tanh(z)
        z * g
    )

let model =
    torch.nn.EmbeddingBag(EMB_INDX_DIM,EMB_DIM)
    ->> torch.nn.Linear(EMB_DIM,BTL_N)
    ->> lisht()
    ->> torch.nn.Dropout(0.1)
    ->> torch.nn.Linear(BTL_N,BTL_N)
    ->> lisht()
    ->> torch.nn.Dropout(0.1)
    ->> torch.nn.Linear(BTL_N,BASE_TGTS)
Product Versions
.NET net7.0 net7.0-android net7.0-ios net7.0-maccatalyst net7.0-macos net7.0-tvos net7.0-windows
Compatible target framework(s)
Additional computed target framework(s)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last updated
0.77.0 101 2/26/2023
0.76.0 112 2/13/2023
0.75.0 98 2/13/2023
0.74.0 100 2/12/2023
0.73.0 217 11/15/2022
0.70.0 206 11/14/2022
0.61.0 287 10/8/2022
0.60.0 364 8/14/2022
0.50.0 295 5/18/2022
0.4.3 306 4/18/2022

Fix deeply nested buffer references when moving model to another device