Light

hololabinc / hololabdnnpackages Goto Github PK

View Code? Open in Web Editor NEW

28.0 4.0 1.0 5.72 MB

The HoloLab DNN Packages providing image recognition library using deep learning running on the Unity. This packages is implemented based on Unity Sentis.

Home Page: https://hololab.co.jp/

License: MIT License

C# 98.31% ShaderLab 1.69%

deep-learning image-recognition sentis unity

hololabdnnpackages's Introduction

HoloLab DNN Packages

About

The HoloLab DNN Packages providing image recognition library using deep learning running on the Unity.
This packages is implemented based on Unity Sentis.

Packages

The HoloLab DNN Packages consists of some packages.
You can use this library by combination of one base package and some task packages.
Please see README of each package about how to use package.

Base Package

jp.co.hololab.dnn.base
This package is providing base class for dnn inference.
This package is used as internal dependency for other packages.
You can create inference classes for your models using this base class too.

Task Packages

jp.co.hololab.dnn.classification
This package is providing classification class using general classification models.
This package contains simple inference sample app to learn how to use classification class.
jp.co.hololab.dnn.objectdetection
This package is providing object detection class using YOLOX model and YOLOv9 MIT model.
This package contains simple inference sample app to learn how to use object detection class.
jp.co.hololab.dnn.depthestimation
This package is providing depth estimation class using general relative depth estimation models.
This package contains simple inference sample app to learn how to use depth estimation class.
jp.co.hololab.dnn.segmentation
This package is providing segmentation class using general segmentation models.
This package contains simple inference sample app to learn how to use segmentation class.

Environment

These packages work on Unity 2023.2 (Unity 6) or later.

License

Copyright © 2024 HoloLab Inc.
All packages are distributed under the MIT license for now.
Please see the license for each package.

hololabdnnpackages's People

Contributors

Stargazers

Watchers

Forkers

hololabdnnpackages's Issues

How to use split inference on webcam via the Segmentation package?

Hi there,

Thank you for the amazing repository, you're really doing some great work here.

I was going through the repository and have been playing around with the Segmentation task. I am particularly curious about the Segment method in SegmentationModel.cs file:

public IEnumerator Segment(Texture2D image, Action<Texture2D> return_callback)
        {
            var output_tensors = new Dictionary<string, Tensor>();
            yield return CoroutineHandler.StartStaticCoroutine(Predict(image, (outputs) => output_tensors = outputs));
            var output_name = runtime_model.outputs[0].name;
            var output_tensor = output_tensors[output_name] as TensorFloat;

            var indices_shape = new TensorShape(1, output_tensor.shape[2], output_tensor.shape[3]);
            var indices = TensorInt.AllocNoData(indices_shape);
            backend.ArgMax(output_tensor, indices, 1, false, false);

            output_tensor.CompleteOperationsAndDownload();
            indices.CompleteOperationsAndDownload();

            var indices_texture = ToTexture(indices);
            var resized_texture = Resize(indices_texture, image.width, image.height);

            indices.Dispose();
            output_tensors.AllDispose();
            MonoBehaviour.Destroy(indices_texture);

            return_callback(resized_texture);
        }

Would it possible for you to provide an example of how to call this function during Update() when running an application that uses Webcam frames for Inference?

Cheers,
Namas

the position of the output has a problem on segmantation

Greetings, first of all, thank you for these packages, they seem very successful and fast. I have not tested it on Android and iOS yet, I only tested it on Windows, but I think there is a small problem with segmentation. When I use the demo, the position of the output seems a little different.

object detection demo with an error

hello
i am using your package to test unity.sentis yolov5 model including classification and object detection.
The classification demo works fine.
but the object detection demo shows some error.
when i tested it with my own yolov5 model.
it shows the index array out of range when it comes to var grid = grids[c] code;
i am not a ai specialist but want to use ai function in unity.
looking forward to your reply soon.

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.