search

yformer / EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Apache License 2.0
2.12k stars 151 forks source link

The output mask with different information granularity #50

Open xwhkkk opened 7 months ago

xwhkkk commented 7 months ago

Hello ! I found a problem when I test a image from coco datasets. For the same point prompt, the output mask has different result with tiny and small model, as the following screenshots. The coordinate of the point prompt is (380,250). image image image

I would like to be able to get a full person segmentation with EfficientSAM-S model, how can I achieve this? Thank you for your suggestions

yformer commented 6 months ago

@xwhkkk, You may need to finetune this model on a person dataset for full person segmentation.