杜英龙

We have created a new branch to integrate AnyLabeling. We have divided the functionality into three functions: point_prompt, box_prompt, and text_prompt, which can be seen as decoders for the model....

We have released the API for FastSAM. Please see for details at fastsam/decoder.py. import model ```python from fastsam import FastSAM ,FastSAMDecoder model = FastSAM('./weights/FastSAM.pt') fastsam = FastSAMDecoder(model,device=DEVICE,retina_masks=True,imgsz=1024,conf=0.4,iou=0.9) ``` Encoder ```Python...

Thank you for your attention, yolov8 uses the method of anchor-free, which is mainly applied to detect branches, and there is no effect on segment branches, indeed Yolov8-seg uses anchor-free...

Hi，When retina=True, higher resolution results are used in post-processing. Usually retina does not affect the result of inference. Can you describe in detail under what mission this happened?:blush:

Thank you for your interest in FastSAM! You can get the mask from the prompt_process function, and then manipulate it with the original image to get the cropped image. https://github.com/CASIA-IVA-Lab/FastSAM/blob/4d153e909f0ad9c8ecd7632566e5a24e21cf0071/Inference.py#L98C64-L98C64...

Thanks for your attention. FastSAM does have this problem at the moment, and we are working on ways to optimize the mask generator. 😊