Alexey234432

Thank you very much for your help. I am facing the same issue with mobilenetV3 (both with PTQ and QAT), any ideas on why this might be the case? Thank...

in my case loss values are slightly higher - is it the same for you? ie 1.072 for 15M model is my case is 1.0833 and 0.760 for 110M model...

I had the same issue and was not able to solve it; it was specifically for MobileNetV3 with Keras / TFLite. If I remember correctly as a workaround I had...

> Hi @Alexey234432. Just for curiosity, did you have any luck with getting the SLIM based implementation working? It's unfortunate that Keras / TFLite doesn't have a solution for this...

any solutions to this?

could you elaborate more please, which instance have you used? is it in AWS? also what was the command? I am trying to run - _CUDA_VISIBLE_DEVICES=-1 python -m llava.serve.cli --model-path...