Old TFLite binary with newer model.

[Techseeker-404]

@boncheolgu got the following error

Finished dev [unoptimized + debuginfo] target(s) in 2m 14s
     Running `target/debug/tftest`
ERROR: Op builtin_code out of range: 127. Are you using old TFLite binary with newer model?
ERROR: Registration failed.

thread 'main' panicked at 'called `Result::unwrap()` on an `Err` value: InternalError("failed to build")', src/main.rs:57:18

tflite model was build and converted using tensorflow-gpu==2.7.0 Host-OS :- Pop_Os(linux X86_64) At some stage, i have plans to cross compile the application to arm architecture for raspberry pi model3

[bugeats]

Same. Did you ever get it figured out?

ERROR: Op builtin_code out of range: 120. Are you using old TFLite binary with newer model?
ERROR: Registration failed.

tflite-rs 0.9.6 and the min_runtime_version metadata in my model.tflite has a buffer value of: 303 (???).

[Techseeker-404]

@bugeats sorry for the delayed response, unfortunately I couldn't figure out the issue. So I moved to tract-onnx which serves well for my need https://github.com/sonos/tract

[inf17101]

I have the same issue when running the yamnet tflite model on x86_64 linux. A solution would be great.

And this library also compiles not on a mac m1 processor.

[Techseeker-404]

I have the same issue when running the yamnet tflite model on x86_64 linux. A solution would be great.

And this library also compiles not on a mac m1 processor.

How about considering the https://github.com/sonos/tract which is an amazing crate.

[inf17101]

Thank you for reply.

I have found a lib that works on all platforms I need. It' s called tflitec and builds on linux x86_64, arm64 and on darwin-arm64 (M1) without problems because it is just a wrapper around tflight C lib. It fits my need because I do not need to export the model in different special formats and the client code of this lib looks straight forward.

Issue can be closed. Thanks