You are not connected. Please Login or Register to fully enjoy this website.
Layer-Based Neural Network 12/Oct/2021 this is Layer Base NeuralNetwork Blueprint can build a NeuralNetwork using several kinds of />Main Class of this Plugin is class have some methods for 'Build Network', 'Train' and />'Layer Class' is Part of are 8 different Layer is constructed by adding several processes the Stacked Layer in order from the input side to the output />you can Train Game AI as explanation is the following />Note: GPU acceleration is not />Layer ClassesAffineConvolutionalGRU (Gated Recurrent Unit)SoftmaxSigmoidReLUSoftplusTanhNglSimpleLayerStackNNMain Class of this Network' : create 'Layer Class' and add to Network by 'AddLayer' : Call 'Train' method with Input-Data and : Call 'Forward' method with Input-Data to Calculate : 'SaveJson' method write network parameter and structure to : 'LoadJson' method construct network structure and read parameter from is possible to construct a neural network easily and flexibly on a save and load learned network ( Json file types of neural network />Code Modules: NglNN (Runtime)Number of Blueprints:9Network Replicated: NoSupported Development Platforms: Win64Supported Target Build Platforms: Notes: Asset Store Marketplace Unreal Unity Manufactured by: nagakagachi 4.20-4.27 Product ID: 79499 5 3 3 3 5 1

View Product

DashboardGrid Release viewBrowse the LibraryThe ArchiveRewardsForum
-

Layer-Based Neural Network(exclu)


uploaded by Anon_527 , Last change: 12-10-2021
Published: , Publisher: nagakagachi
Price: 5 USD - Size: 22.27 MB

File version


Product description

this is Layer Base NeuralNetwork Blueprint Plugin.

you can build a NeuralNetwork using several kinds of Layers.


Main Class of this Plugin is "NglSimpleLayerStackNN".

this class have some methods for "Build Network", "Train" and "Inference".


"Layer Class" is Part of NglSimpleLayerStackNN.
There are 8 different Layer Classes.

NglSimpleLayerStackNN is constructed by adding several Layers.

NglSimpleLayerStackNN processes the Stacked Layer in order from the input side to the output side.


you can Train Game AI as follows.

https://youtu.be/JMm5Z8aykXc

The explanation is the following URL.

https://github.com/nagakagachi/ue4/wiki/NglNN-Sample-2


Note: GPU acceleration is not supported.


Layer Classes

  • Affine
  • Convolutional
  • GRU (Gated Recurrent Unit)
  • Softmax
  • Sigmoid
  • ReLU
  • Softplus
  • Tanh


NglSimpleLayerStackNN

  • Main Class of this Plugin.
  • "Construct Network" : create "Layer Class" and add to Network by "AddLayer" method.
  • "Train" : Call "Train" method with Input-Data and Teach-Data.
  • "Inference" : Call "Forward" method with Input-Data to Calculate Output.
  • "Save" : "SaveJson" method write network parameter and structure to Json.
  • "Load" : "LoadJson" method construct network structure and read parameter from Json.


Documents

https://github.com/nagakagachi/ue4/wiki/NglNN

https://github.com/nagakagachi/ue4/wiki/NglNN-Sample-1

https://github.com/nagakagachi/ue4/wiki/NglNN-Sample-2

Features:

  • It is possible to construct a neural network easily and flexibly on a Blueprint.
  • Support save and load learned network ( Json file ).
  • 8 types of neural network layer.


Code Modules:

  •  NglNN (Runtime)


Number of Blueprints:9

Network Replicated: No

Supported Development Platforms: Win64

Supported Target Build Platforms: Win64

Documentation:

https://github.com/nagakagachi/ue4/wiki/NglNN

https://github.com/nagakagachi/ue4/wiki/NglNN-Sample-1

https://github.com/nagakagachi/ue4/wiki/NglNN-Sample-2

Example Project:

https://drive.google.com/open?id=1HTphRSsPFSyIX4EfFdioEYojri0pCYkz

https://drive.google.com/open?id=1-yjFjeNzXaHkJtcnDTizODeVMtgZBSF1

Important/Additional Notes:

You can add a (short) comment to this game asset and send it to approval (you can edit it later on)

You can add a review to this game asset and send it to approval (you can edit it later)


There are no thanks for this product yet.

© 2021 - Fair Use Statement | DMCA Statement | Privacy Policy
Idea, coding and concept: pXNfdegskxB/R2PwLdwDabnAr+pJdcTZXc5F8kYndSk6lQ/M6uzS3Bi2lh+df9ElmWumI553tQvJj8yHmGg0Og==
Copyright Disclaimer Under Section 107 of the Copyright Act 1976, allowance is made for "fair use" for purposes such as criticism, comment, news reporting, teaching, scholarship, and research.
Fair use is a use permitted by copyright statute that might otherwise be infringing. Non-profit, educational or personal use tips the balance in favor of fair use.


This work is licensed under a Creative Commons Attribution 4.0 International License.