Owl-Vit-SAM

Using nature language to segement everything

Installation

Installing both PyTorch and TorchVision with CUDA support is strongly recommended.

Install Segment Anything:

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

Install OWL-ViT (the OWL-ViT is included in transformer library):

pip install transformers

Run

python main.py

Results

result images will be saved in the folder ./outputs