Ryan OShea

Hi, The warnings get called on any layer that uses the deprecated functions, so the more layers that use the function, the more warnings. I will try to run this...

Hi @kylesayrs , It looks like a tflite runtime error rather than an armnn layer error, So I doubt it has anything to do with layer norm (yet?). As Shelton...

We have this [quick start guide](https://github.com/ARM-software/armnn/tree/HEAD/delegate/DelegateQuickStartGuide.md) or this [slightly more in-depth guide](https://developer.arm.com/documentation/102561/2111/Overview-of-running-the-application/Run-the-application) that might be able to help you. [Options can be found here](https://github.com/ARM-software/armnn/tree/HEAD/delegate/include/DelegateOptions.hpp) Adding the directory of the libarmnn.so...

Hi @luchangli03 , What version of ArmNN/Compute Library are you using? If you are using v22.05 or v22.08, Could try this option: ``` * Option key: "allow-expanded-dims" \n * Possible...

Does the option mentioned in the comment above help fix the issue?

Hmm, I just noticed there was a patch put up to remove ethos u as coprocessor, but this patch fixes that issue if it was intended to use ethos u?...

I would prefer option 1 as its very easy to skip the disclaimer and look straight at the numbers

Hey @Unbinilium, if you have access to the non tflite model could you try converting it with the `converter._experimental_disable_per_channel_quantization_for_dense_layers = True` flag and see if the issue is resolved? Ah...

Hey @zyw02 , could you provide more details? eg. Model, hardware, are you using reference kernels or optimized kernels, tflm version, any logs or profiling that you did

#2630