search

z-x-yang / Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
GNU Affero General Public License v3.0
2.75k stars 332 forks source link

latest installation notes win #134

Open Spr-Peach opened 5 months ago

Spr-Peach commented 5 months ago

my python=3.10 and cuda=11.8

installation: download both zip.exe and unzip.exe from the url, put them into a folder & add the folder path to environment variables.

git clone https://github.com/z-x-yang/Segment-and-Track-Anything.git
python -m venv venv
venv\scripts\activate.bat
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118
cd sam
pip install -e .
cd..
pip install -e git+https://github.com/IDEA-Research/GroundingDINO.git@main#egg=GroundingDINO
pip install numpy opencv-python pycocotools matplotlib Pillow==9.2.0 scikit-image
pip install gradio==3.39.0 gdown ffmpeg==1.4
git clone https://github.com/ClementPinard/Pytorch-Correlation-extension.git
cd Pytorch-Correlation-extension
cd..

model: create a new folder named "ckpt" at ./ download these .pth files below and drop them into sam_vit_b_01ec64.pth R50_DeAOTL_PRE_YTB_DAV.pth groundingdino_swint_ogc.pth

running:

python app.py
cyandddd commented 2 months ago

我按照你这个做了，然后出现了以下错误：

https://github.com/z-x-yang/Segment-and-Track-Anything/issues/158#issue-2342660812

不好意思我是个小白。。。不太搞得懂到底是什么问题，要怎么解决。可以帮我吗？谢谢！！