Skip to content

XiaoYou201/auto-label-anything

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Quciky start

Install segment anything, reference official repository.

The code requires python>=3.8, as well as pytorch>=1.7 and torchvision>=0.8. Please follow the instructions here to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.

Install Segment Anything:

pip install git+https://github.com/facebookresearch/segment-anything.git

or clone the repository locally and install with

git clone git@github.com:facebookresearch/segment-anything.git
cd segment-anything; pip install -e .

The following optional dependencies are necessary for mask post-processing, saving masks in COCO format, the example notebooks, and exporting the model in ONNX format. jupyter is also required to run the example notebooks.

pip install opencv-python pycocotools matplotlib onnxruntime onnx

Then Download segment-anything model and move them to sam directory (if not exist, you can make a new directory named sam in root dir)

default or vit_h: ViT-H SAM model.
vit_l: ViT-L SAM model.
vit_b: ViT-B SAM model.

Install tranformers, reference offcial web.

pip install transformers

When you installed above two model, you can run this program through main function.You can modify args to do that you want.
Have fun~

About

auto-label-anything

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages