I would like to see examples of Object Detection using YOLO and SSD implemented in Julia.
Has anyone tried this before?
YOLO.jl has a knet backend.
ObjectDetector is a bit more featured, with a Flux backend.
https://github.com/r3tex/ObjectDetector.jl
There’s also a wrapper of AlexeyAB’s fork of Darknet
https://github.com/IanButterworth/Darknet.jl
I linked to your YOLO partly because your README has pointers to other related projects
Great, this helps.
Also the performance, what is the best way to measure the performance in terms of memory footprint and training and inference time ?
Bumping the topic a bit. I also found: https://github.com/DhairyaLGandhi/maskrcnn
Does any of them have the training capability as well? At least to un-freeze the last layers because I would need to re-train them on a custom dataset.