@dusx

Thank you. Managed to do this with the help of Claude Sonnet 4.6  which showed me how to retrain the data using something which has the same landmarks as in your Mediapipe pose tracking examples.
This seems to work very well, thank you. 

Not sure how to share the process? 

I took maybe 25 photos of each of 14 poses (yes, different handstand shapes, of course!)

Then organised them into this folder structure

training_data/
    arms_crossed/
        photo1.jpg
        photo2.jpg
        ...
    arms_raised/
        photo1.jpg
        ...
    lunge_left/
        ...

And then followed Claude's instructions. 

Here's my Colab notebook:
https://colab.research.google....

After I'd successfully trained that and got the files out the other end...

It then gave me the python mediapipe code. 
https://www.dropbox.com/scl/fi...

And that outputs the OSC into Isadora. Two streams, one telling me which pose it is, and the other giving me the confidence about it.

Hope this is useful to someone!!!

Cheers

Mark (not that Mark, who I'm sure doesn't use Claude to do his coding!)

@mark_m

I haven't gone through this in some time. I will go through this tomorrow, and see what needs to be updated to make the process smooth once again. My gut tells me it would be better to use the current format/s supported by Teachable Machine, and update the libs / code used to work with the current format.

Hello Isadormobiles,
I've been following @Andy-Carluccio 's  tutorial on Teaching Isadora to recognise images, object, people, which is here:
https://support.troikatronix.c...

I've run into a couple of issues - perhaps not surprising, as Andy wrote this five years ago!
1. The tensorflow models produced by Teachable Machine are now in .js format, not the .h5 that Andy's NDI Classify program wants.
With help from Claude AI I did convert the Tensorflow model to .h5

2. When I run the NDI_classify.exe I briefly see a window flash open, and that's it. No dialogue box as expected. Tried on two different PCs, so... 
@Andy-Carluccio in the instructions it says "run NDI-Classify.exe" I didthis just by double clicking. Is there a particular way I should be running it?

Time has moved on, and perhaps this is no longer the best way to achieve this? I have this well trained tensorflow model which I want to use in Isadora to trigger events when the different human poses are detected. Shape A triggers event A, Shape B triggers event B, etc.

Any thoughts on this? 

Thanks all!!


Mark (not...)

@skuven said:

Is there any intention to make actors that produce sound but from the pre 4.5 release (aud) have new audio outputs? for example, the 'speak text' actor doesn't have an audio output connector, but internally it must connect to the audio engine? I would like to be able to apply reverb and FX to that through the new audio connections workflow, etc. that would allow some creative uses of the tools already included.

 I have a feature request in to give audio output to, for example, the Tone Generator and Speak Text actors, but it's not on the immediate roadmap at this time. It is still possible to do this with virtual audio routing software like Blackhole thanks to the Audio Input actor. (Speak Text actor --> Virtual Audio Cable --> Audio Input actor --> audio effects --> Audio Output actor)

---

@skuven 

the 'speak text' actor doesn't have an audio output connector, but internally it must connect to the audio engine? 

Certain things in Isadora process audio differently, and while some share the same processes, others don't, so there's not one unified "audio engine" that all actors can push audio into and pull audio out of. If I remember correctly, the Speak Text and Tone Generator actors rely on different audio processes than the new audio actors, so it's not as simple as just slapping an audio output on them.

@dusx Is there any intention to make actors that produce sound but from the pre 4.5 release (aud) have new audio outputs? for example, the 'speak text' actor doesn't have an audio output connector, but internally it must connect to the audio engine? I would like to be able to apply reverb and FX to that through the new audio connections workflow, etc. that would allow some creative uses of the tools already included.

RESPECT and Thanks!

@notdoc said:

Isadoronauts

 I love that!

H

wow. just wow. 

roll on the weekend, when i can clear some play time. Thanks Isadoronauts for your labours, and your listening.

can't wait

x

@woland good idea. thank you, will look into it

@woland Thanks a lot. That makes sense... ;o)