How to integrate my own tflite model on Flutter?

Question

I have completed a tensorflow model than converted it correctly to tflite in order to use it in a mobile app using flutter. I didn't know how to integrate a personalized tflite model with flutter. All the available examples use the pretrained models. When I tried my model, the camera launches for a while and stops immediately! enter image description here

I followed the source code from this link which uses the "tflite" pacakge : https://medium.com/@shaqian629/real-time-object-detection-in-flutter-b31c7ff9ef96 I added my own tflite model alongside with other models in all the ".dart" files and in "pubspec.yaml".

In my opinion you just need to follow the article, replace the model with our own and verify if all the model inputs and outputs are correct. I think that this description lacks more information to be able to help more precisely :) — Julian Modlinski
– Julian Modlinski, Commented Mar 29, 2022 at 15:01

user19792351 · Accepted Answer · 2022-08-18 09:13:43Z

2

you can try the 'tflite_flutter' package. 'tflite' package is not suitable for custom trained models as you will get shape incompatible error message

answered Aug 18, 2022 at 9:13

user19792351

212 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

How to integrate my own tflite model on Flutter?

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related