Marc Rousavy

Hey - this is currently not supported in Fast TFLite. Shouldn't be too tricky to add though

The link from the docs should be a hint on how to get started, I personally don't have any plans to implement this right now unless someone pays me to...

Interesting - yea maybe we can expose this differently by making the tensors in `inputs` read-write as well? Not sure if that'd be a good API design as it's probably...

Yea if you can make it optional, same way as CoreML, that would be great. Add an enum to it and i'll merge it

Honestly not sure why this is failing, might be interesting to see if TFLite works for Simulators or if they have some patches for that.

Do you have ProGuard enabled?

Maybe add this to your `proguard-rules.pro`: ```pro -keep class com.mrousavy.camera.** { *; } ```

Hey - thanks for your PR! > It appears that this issue is resolved in the TensorFlow Lite nightly version I am building TensorFlow Lite from source from their current...

Ah I see - I think this approach is not really good since it blocks simulators / makes it harder to use on simulators. I think we can compile `TensorFlowLiteC`...

See https://github.com/mrousavy/react-native-fast-tflite/pull/26