search

ymy-k / Hi-SAM

[arXiv preprint] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation
Apache License 2.0
193 stars 10 forks source link

Poor Paragraph segmentation quality #8

Closed SeonjiPark closed 3 months ago

SeonjiPark commented 5 months ago

Hi, thanks for sharing your work.

By the way, I found your demo_hisam.py shows poor quality. I tried to use demo_hisam.py following your direction,

python demo_hisam.py --checkpoint pretrained_checkpoint/hi_sam_l.pth --model-type vit_l --input demo/2e0cb33320757201.jpg --output demo/ --hier_det

This is how i executed the your code and i get the result below. (Even pretrained weight trained by HierText, which contains input image) 2e0cb33320757201

Could you tell me If I made mistake using demo by any chance ?

ymy-k commented 5 months ago

Change the point prompt position in the code.

decadance-dance commented 3 months ago

Change the point prompt position in the code.

How to disable prompting at all?

ymy-k commented 3 months ago

Please see AMG and refer to the paper.