Available material:
Hello, I have tried the extension in android emulators, studio and genymotion, and it doesn't work. It is important in the classroom to be able to use these emulators with our students, due to the variety of mobiles they have.
It would be very useful if the extension were adapted.
Thank you for your work.
Welcome @garridoferfer .
Did you load the provided aia Fernando and use it with Companion and a real device?
Of course the example does not work in an emulator. It does work on a cell phone.
To use the example that is provided with the extension you must use a camera. I am not aware of any emulator that has camera hardware.
Hello, in Companion and in android emulators it doesn't work, but it does in real device.
Thanks.
Is there a way to use mobile front camera to capture image ?
At the moment with this version of the extension there is no possibility to capture images with the mobile front camera.
ok , I will look forward for this update in future.
hello, is it possible to use the extension with the device offline?
Hello, this version of the extension does not allow an offline use.
Hello..
I'm the beginner, I would need someone who can kindly help me step by step on developing my app:pray:
.
How can I add videos of the identified object using this version of extension.
Hello
This version of the extension does not enable the addition of videos of the identified object.
Ok thanks
Hello, is there a way to classify an image with this extension?
Hello, currently its only possible to classify pictures taken with the camera. More information: Computação na Escola
Hi
I am using the above model in my app but it doesnt seem to work . Can someone please help. The model works in the browser. app is attached below, I am using Android 13 google phone, MIT AI Companion recently downloaded.
Plant_disease_detection.aia (469.4 KB)
Hi, there seems to be a problem with the .tm model you exported, as in the app it keeps running, never returning any classification result. Did you export the Tensorflow.js version?
I used the URL which is generated when we upload the model. Should I try doing that again from scratch?
Hi, yes I would suggest that - you need to export as Tensorflow.js. I just tried your app with a TM model I trained rapidly just for testing (Teachable Machine) and with this model your app terminates running the model. So I guess the problem is related to the model you exported from Google Teachable Machine.
This gets downloaded as a zip file.
How can we use it in MIT App Inventor
Hi you have to upload the Tensorflow.js model and then use the link int the TMIC extension.
