Alexander Efimov
Alexander Efimov
+cc @chunseoklee
@chunseoklee Yes, we can do it. The only thing you should know is that this ( model measured in #5080) is a "toy" example, so it is not actually very...
> means sine generator model on tf-micro site, right ? Yes, this is about sin(x) model. It is a normal tflite model (you can cut it from examples, save as...
`Keyword` model has some issues: it does not have some fields and does not verify. In order to extract it from char array I've used some hacks on tensorflow code:...
Model looks like this: 
cut model: [model_1-12.tflite.zip](https://github.com/Samsung/ONE/files/7140248/model_1-12.tflite.zip) cut model with softmax: [model_1-13.tflite.zip](https://github.com/Samsung/ONE/files/7143375/model_1-13.tflite.zip) Another issue I noticed is SVDF operator takes additional tensor as input and modifies it in-place. This is neither constant nor input...
@chunseoklee Sorry for the delayed status =_= @SlavikMIPT is benchmarking luci interpreter. We faced some issues with both target models: - keyword model uses experimental SVDF operation that is not...
@SlavikMIPT Could you measure it again with new tflite? Just to be sure data is fresh =)
@SlavikMIPT > tflite micro: Finished in 6747161us > luci: Finished in 4766142us This is really interesting results, thank you!
> I also ran the benchmarks with model placed in RAM not in FLASH on tflite-micro - inference time has increased on ~10% This is extremely unexpected results for me...