Gregor Scholz
Gregor Scholz
I never tried a model that takes strings as an input, but if I remeber correctly, sometimes i got similar error messages for `int8` while doing the [object detection](https://github.com/tensorflow/flutter-tflite/tree/main/example/object_detection_ssd_mobilenet) example....
Can you please provide some screenshots? Maybe look at the `label.txt`. The model does not recognise that many things.
Maybe its the phone, do you have another phone you can test it with?
can you maybe show more code? it is hard to tell whats wrong from this snippet
Did you double check if the model is correct? Maybe there is some error with the model?
Oh sorry, yea, mb. I think i've read some time back someone had also problems with ios release build while it worked in debug. I will try to find it...
Try using `interpreter.getOutputTensors()` and `interpreter.getInputTensors()`. As the name suggests they return a List of Tensors which get expected. You could call `interpreter.getInputTensors().forEach((tensor) => print(tensor))` to get every input tensor, same...
I am not completly sure, your expected input shape is `[1, 256, 256, 3]` but according to this one comment your input shape is `[1, 300, 300, 3]`. Also the...
Can you print out `_interpreter!.getInputTensors()` and `_interpreter!.getOutputTensors()`. Maybe your model takes multiple tensors as in- or output tensors.
There you can see that you have two different output tensors. Your desired input shape is `[1, 256, 256, 3]` and your desired output shapes are `[1, 12276, 4]` and...