Closed ManosMpampis closed 7 months ago
I suggest not merging this until #488 is reviewed and ready to be merged as well, as i think it would complicate #488's review. @omichel @ManosMpampis @passalis.
Thank you for your comments @tsampazk and @omichel. @tsampazk Yes, I think it is better to review #488 and then merge that PR, so that if something needs to be changed in #488 it doesn't clutter this PR as well.
This PR aims to translate some changes of #488 into C API and simplify some optimizations for smaller memory footprint during inference and optimizations. Adds dynamic shape capabilities into JIT optimizations for Python and C APIs. Fix some buggs with C APIs during model export and when the output had zero bounding boxes.