https://github.com/AILab-CVC/YOLO-World

git clone --recursive https://github.com/2829788992/CV.git

conda create --n yolow python=3.8 -y
conda activate yolow

conda install pytorch==1.11.0 torchvision==0.12.0 torchaudio==0.11.0 cudatoolkit=11.3

pip install -U openmim
mim install mmcv==2.0.1
mim install mmdet==3.3.0
mim install mmengine==0.10.3
mim install mmyolo==0.6.0

git clone https://github.com/open-mmlab/mmyolo.git
pip install -r requirements/albu.txt
mim install -v -e .

pip install supervision
pip install transformers

在image_demo.py中设置端口

os.environ["HTTP_PROXY"] = "http:https://127.0.0.1:7897"
os.environ["HTTPS_PROXY"] = "http:https://127.0.0.1:7897"

其中 http:https://proxy_ip_address:port 中的 proxy_ip_address 和 port为开启科学上网后的地址和端口

See demo for more details

• gradio_demo.py: Gradio demo, ONNX export
• image_demo.py: inference with images or a directory of images
• simple_demo.py: a simple demo of YOLO-World, using array (instead of path as input).
• video_demo.py: inference YOLO-World on videos.
• inference.ipynb: jupyter notebook for YOLO-World.

python image_demo.py ./configs/pretrain/yolo_world_v2_s_vlpan_bn_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py ./weights/yolo_world_v2_s_obj365v1_goldg_pretrain-55b943ea.pth ./data\coco\val2017 'person,dog,cat' --topk 10 --threshold 0.01 --output-dir demo_outputs