search

leondgarse / keras_cv_attention_models

Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionnext,lcnet,levit,maxvit,mobilevit,moganet,nat,nfnets,pvt,swin,tinynet,tinyvit,uniformer,volo,vanillanet,yolor,yolov7,yolov8,yolox,gpt2,llama2, alias kecam
MIT License
576 stars 89 forks source link

yolov8 instance segmentation #160

Open sak-codes opened 2 months ago

sak-codes commented 2 months ago

Thanks for implementing these amazing models! I wonder if there's any implementation for yolov8 instance segmentation. It would be a nice addition if the repo doesn't have it.

Thanks once again.

leondgarse commented 2 months ago

I think the inference model should be easy, but the training method may not. As they have made it rather convient for using, I'm rather lazy porting that, lol.

sak-codes commented 2 months ago

Thanks for the quick response. Can you please show how it can be inferred using Keras? Thank you.

leondgarse commented 2 months ago

Just uploaded a testing one temp adding YOLOV8_N_SEG. But segmentation decoding process still missing.

from keras_cv_attention_models import yolov8
mm = yolov8.YOLOV8_N_SEG()
leondgarse commented 2 months ago

Ok, YOLOV8 segmentation models uploaded yolov8#segmentation-models, but inference only.

sak-codes commented 2 months ago

Thank you so much for your help.