Hi. I have created a onnx file after building an image segmentation model that works to segment feet.
I am unable to figure out how to deploy this to unity.

The model is based on this notebook.
https://nbviewer.jupyter.org/github/fastai/course-v3/blob/master/nbs/dl1/lesson3-camvid.ipynb

I used the same method and exported the model to onnx format.

Would you able to point me to a direction where I can do this ?

I am downing the ml-agents file from the github link you provide,and use anaconda prompt to cd to the destination of converter.py,and type the code ,python tensorflow_to_barracuda.py my.pb destination the output destination,And it cames out that there is no mlagents module.
I donot know why

Hi,
First of all great project, reall useful. I am trying to do face detection specifically instead of object detection, so I need an onnx tiny yolo model trained for this task. I was able to find a pre-trained keras model so its extension is h5. I saw that you converted tiny yolo model to onnx with the tool called OnnxMLTools. I am using keras2onnx but the input's shape turns out to be (1, 416, 3, 416) instead of (1, 416, 416, 3) and I believe this creates a problem. Can you please explain how to use OnnxMLTools because I wasn't able to figure out how to use it after reading the readme file?

Hi, I just wanted to ask if you have made any attempts to run Barracuda inference engine on a custom render texture as I can see that in your work you have incorporated the use webcam texture(api).

But I am planning to run yolo on Barracuda using Render Texture instead, can I ask if its possible using your work and could you point me in the right direction if possible.

Thanks a lot!

Hi,

I am trying to use this for object detection. I want to combine this with AR. For example, on detecting a object DOG, instead of drawing a bounding box, I want to show a animation in that area. I don't have good knowledge on Unity as I am using it for the first time. Is it possible? If yes, can you point to any references that would be helpful

The project seems to work in my laptop but when I compile the apk and try to run it in my Android smartphone (Xiaomi Redmi Note 7), it inmediately crushes. Here I present a screenshot of the app when I point at my laptop. The image randomly crops and duplicates and everything start to shake. Why might this be happening? Thank you.

@Syn-McJ Do you know if it is possible to run this project on a set of AR glasses?

Hi, I have been trying to deploy a cyclegan model into unity with Barracuda, but I have failed many times. I have tried different methods and other pretrained models from Internet. Usually the errors like missing layers(I am not sure if this will affect the usage of the model, I have one converted successfully to nn with missing layers, but failed when run on Android), -1 not supported by lamda... I am actually having no experiences in neural network, so I am kind of struggling now. Any suggestions? I have tried tensorflowsharp too, I cannot even compile it with ARcore. Are there any other plugins that I should shoot for?

I would like to know if it would be possible to get a Teachable Machine model into Unity and use it with Barracuda Currently I have tried to convert a Tensorflow model with tensorflow_to_barracuda.py which I get this error: google.protobuf.message.DecodeError: Error parsing message

I have also tried to convert the model with the tf2onnxt but when I have successfully convert the model and import it the model has warnings

also when I import any model of my own the camera is responding every second

-Unity version 2020.1
-Barracuda version have tried with 0.4.0 and 0.6.3

Hope Teachable Machine models is possible to use since it's fast and easy for the project i am working on

I made sure all dependencies are as specified and even changed python dependencies for Barracuda, however, the app crashes after a few seconds of running it. I have Unity 2019.3.2 and Using Barracuda 0.4.0. The errors I am getting are

I made sure everything is set correctly in every object as specified in the descriptions. Is there something I am missing?

Hey @Syn-McJ,
I'm just looking for some advice regarding my model. I tried making my own yolov2-tiny model (on 1 class) to deploy on Unity. I am not an expert on YOLO models. The output grid shape is different than your description on the website, also it is different from the graph you have in your repository. I was wondering how you did the calculations based on the graph you had to be able to get results. I looked at the microsoft website to get more familiar with their procedures, however, calculations done in Unity is a bit different.
As of now, the result I am getting for confidence or results is NaN which is most likely due to miscalculations. My whole model is different, but it works when I use darknet detector source code with an image.
Do you have any idea or resources that can help me?