NVIDIA-AI-IOT / nanosam

A distilled Segment Anything (SAM) model capable of running real-time with NVIDIA TensorRT

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

How can I write a generator based on this foundation

Xcccck opened this issue · comments

commented

Hi,
Thanks for this good job!!
I have completed the use of Predictor, now I want to implement a Generator
just like the code in the mobileSam
But i dont know how to do it , it's so hard for me , i need some help
Thanks a lot
''' like this , i want to get whole masks by Generator'''
def get_mask(srcImg, model):
mask_generator = SamAutomaticMaskGenerator(model)
masks = mask_generator.generate(srcImg)
return masks

Hi, I am interested in the same problem. Were you able to try this?