TYoshimura.TensorShader
5.5.3
See the version list below for details.
dotnet add package TYoshimura.TensorShader --version 5.5.3
NuGet\Install-Package TYoshimura.TensorShader -Version 5.5.3
<PackageReference Include="TYoshimura.TensorShader" Version="5.5.3" />
paket add TYoshimura.TensorShader --version 5.5.3
#r "nuget: TYoshimura.TensorShader, 5.5.3"
// Install TYoshimura.TensorShader as a Cake Addin #addin nuget:?package=TYoshimura.TensorShader&version=5.5.3 // Install TYoshimura.TensorShader as a Cake Tool #tool nuget:?package=TYoshimura.TensorShader&version=5.5.3
TensorShader
Deep Learning .NET library, For Regression.
Description
I tried to create a deep learning library of Define and Run / NHWC format from scratch.
Supports High-Dimensional Convolution Neural Networks. (Complex, Quaternion, Vector3D)
For regression problems: High precision calculate by FP32-FP32 arithmetic (1/8 error of FP32 arithmetic)
Requirement
.NET 5.0
CUDA 10+, Compute Capability 5.0+
validated: Windows experiment: Linux, MacOS
Recommended to Install
CUDNN 7,8 (See MNIST sample to enable.)
Usage
Supported Functions
- Connection Layers
- Real
- Convolution 1D,2D,3D and Pointwise/Depthwise
- Dense
- Complex
- Convolution 1D,2D,3D
- Dense
- Quaternion
- Convolution 1D,2D,3D
- Dense
- Trivector (UnitState : Vector3D, Weight : Quaternion)
- Convolution 1D,2D,3D
- Dense
- Real
- Pooling
- Max Average
- Sizing
- ZeroPad EdgePad Trim
- NeighborZoom LinearZoom
- Array Manipulation
- Sort ArgSort Flip Reshape Concat Separate
- ChannelToSpace SpaceToChannel 1D,2D,3D
- ImageToColumn 1D,2D,3D
- ExtractChannel Sum
- Real Functions
- Add Sub Mul Div Abs Sign Pow Sqrt Square Cbrt Cube Rsqrt Neg Rcp
- Sin Cos Tan Arcsin Arccos Arctan Sinh Cosh Tanh LogCosh
- Exp Log Floor Ceil Clip Step NanAsZero Maximum Minimum
- Complex Functions
- Mul Square Conjugate Squash NonlinearDecay RRelu ZRelu Normalize
- Quaternion Functions
- Mul Square Conjugate Squash NonlinearDecay RRelu Normalize
- Trivector Functions
- QuaternionMul Length Norm CrossProduct Squash NonlinearDecay Normalize
- Aggregation Functions
- Max Min Mean Sum SquareSum SquareMean Variance
- Logical Functions
- Equal NotEqual GreaterThan LessThan GreaterThanOrEqual LessThanOrEqual
- And Or Not Xor
- IsNan IsFinite
- Activation Functions
- Relu Elu LeakyRelu SoftPlus Softmax Sigmoid
- Loss Functions
- SoftmaxCrossEntropy AbsoluteError SquareError HingeLoss HuberLoss MultiBoxLoss
- Optimizers
- SGD MomentumSGD NesterovAG AdaGrad AdaDelta Adam Adamax RMSprop RMSpropGraves Nadam
- Random Generation
- Uniform Normal BernoulliBinary
- Experimentals
- Yamatani Activation
See also...
Install
Download DLL
Download Nuget package
- To install, just import the DLL.
- This library does not change the environment at all.
Licence
Author
Troubleshooting
Can't load Cuda dll!
→Install GeForce Experience and Cuda. Check your environment variables.
System.BadImageFormatException is thrown and DLL cannot be loaded!
→Specify x64 as the project platform.
Product | Versions Compatible and additional computed target framework versions. |
---|---|
.NET | net5.0 is compatible. net5.0-windows was computed. net6.0 was computed. net6.0-android was computed. net6.0-ios was computed. net6.0-maccatalyst was computed. net6.0-macos was computed. net6.0-tvos was computed. net6.0-windows was computed. net7.0 was computed. net7.0-android was computed. net7.0-ios was computed. net7.0-maccatalyst was computed. net7.0-macos was computed. net7.0-tvos was computed. net7.0-windows was computed. net8.0 was computed. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. |
-
net5.0
- No dependencies.
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
Fix IEnum -> IReadonlyList