configs/pretrain_v1/README.md

Pre-training YOLO-World-v1

The YOLO-World-v1 is an initial version, and now is nearly deprecated! We strongly suggest you use the latest version.

Zero-shot Inference on LVIS dataset

model	Pre-train Data	Size	APmini	APr	APc	APf	APval	APr	APc	APf	weights
YOLO-World-S	O365+GoldG	640	24.3	16.6	22.1	27.7	17.8	11.0	14.8	24.0	HF Checkpoints 🤗
YOLO-World-M	O365+GoldG	640	28.6	19.7	26.6	31.9	22.3	16.2	19.0	28.7	HF Checkpoints 🤗
YOLO-World-L	O365+GoldG	640	32.5	22.3	30.6	36.1	24.8	17.8	22.4	32.5	HF Checkpoints 🤗
YOLO-World-L	O365+GoldG+CC3M-Lite	640	33.0	23.6	32.0	35.5	25.3	18.0	22.1	32.1	HF Checkpoints 🤗
YOLO-World-X	O365+GoldG+CC3M-Lite	640	33.4	24.4	31.6	36.6	26.6	19.2	23.5	33.2	HF Checkpoints 🤗

NOTE:

1. AP^mini: evaluated on LVIS minival.
2. AP^val: evaluated on LVIS val 1.0.
3. HuggingFace Mirror provides the mirror of HuggingFace, which is a choice for users who are unable to reach.