Train a model for multilabel image

Hello everyone,
I’m stuck in which is a better approach to train a model for multilabel image because the process i’m using right now is too time consuming can anyone help me which is the best way to train a model. Thanks

please, more details about what you’re trying to achieve and what you’ve tried so far

I’m trying get size of horns but it difficult to measure because horn shape is curve

One more thing which pretrained model i have to use for detect deer and his horns.
Thanks for your response

unlikely, that you’ll find a pretrained one for this.
(also getting data to train your own will prove a challenge …)

is we can use labelme .json file for image for training and how will i use

also is we use polygen data with yolov3