pkgoogle

Hi @vitalii-vorobiov, I would try with r2.15 and go backwards until you have something stable... there may be some weird interactions with iOS and xcode if you go too far...

I was able to replicate with the attached gist. @abattery, can you please take a look? Thanks.

Hi @MinaBabahaji-ML, I followed your directions exactly with a fresh git clone, on this step: ``` adb shell "cd /data/local/tmp && LD_LIBRARY_PATH=. ./model_test --model=model_files/sample.tflite --output_shape=1,26,3" ``` I get this error:...

Hi @MinaBabahaji-ML, Thank you... I have openCL installed on my mac and my AVD has graphics set to Automatic and I run into this issue: ```sh adb shell "cd /data/local/tmp...

Hi @kubaraczkowski, can you please share your model.tflite file used in this step of reproducing: ```sh bash tensorflow/lite/tools/build_aar.sh \ --input_models=model.tflite \ --target_archs=arm64-v8a ``` Thanks!

I was able to reproduce with the original steps and the uploaded whisper model. Hi @terryheo, can you please take a look? Thanks.

Hi VanBap, can you upload your .h5 and .tflite file? That will help me test this faster.

Hi @VanBap, in your notebook you do not specify a specific input_shape in the API: https://keras.io/api/applications/resnet/#resnet50-function, Resizing the converted input shape is actually expected: https://www.tensorflow.org/lite/guide/inference#run_inference_with_dynamic_shape_model, so given your parameters, I...

Hi @VanBap, no worries, if you have no more open items, please feel free to close as completed. Thanks.

Hi @abattery, can you please take a look or comment on this? Thanks.