search

ByungKwanLee / Full-Segment-Anything

This is Pytorch Implementation Code for adding new features in code of Segment-Anything. Here, the features support batch-input on the full-grid prompt (automatic mask generation) with post-processing: removing duplicated or small regions and holes, under flexible input image size
MIT License
119 stars 9 forks source link

Could use an install guide #5

Open hexcreator opened 4 months ago

hexcreator commented 4 months ago

Hello, I'd like to use this but I don't know how to download the pth model or set this up. It'd also be useful if it was setup like a package, so we could install it more easily:

pip install git+https://github.com/ByungKwanLee/Full-Segment-Anything.git
ByungKwanLee commented 4 months ago

Hi! Full-Segment-Anything code is slight change version of code from Segment-Anything which is the original code from Meta.

Therefore, you can download from https://github.com/facebookresearch/segment-anything?tab=readme-ov-file#model-checkpoints!

AntonisCSt commented 1 month ago

Hi! Full-Segment-Anything code is slight change version of code from Segment-Anything which is the original code from Meta.

Therefore, you can download from https://github.com/facebookresearch/segment-anything?tab=readme-ov-file#model-checkpoints!

Still, even the steps after installing the original SAM would be very helpful! (Btw thank you a lot of this work!)