Open Meicsu199345 opened 1 month ago
Hi @Meicsu199345, sorry for the late reply!! Thanks for your interest in YOLO-World!
torch~=1.13
and requirements.txt
to install is fine and we'll remove the support for torch~2.0.SimpleYOLOWorldDetector
now.Hi @Meicsu199345, sorry for the late reply!! Thanks for your interest in YOLO-World!
- Using
torch~=1.13
andrequirements.txt
to install is fine and we'll remove the support for torch~2.0.- We only freeze the CLIP backbone for fine-tuning, other parameters are trainable. If you have a large vocabulary, you can also make CLIP trainable.
- For prompt tuning, you can refer to docs/prompt_yolo_world. You just need to precompute the text embeddings and use the
SimpleYOLOWorldDetector
now.- The pseudo labels are listed here: docs/data.
- The repo is independent from Ultralytics and we only support re-parameterization in this repo.
Thank you very much for your answer~
Question
Thanks for your work,excellent! background I have a dataset about risk_control 100classes 200k images and 400k bboxes。 class such as 1:vulgar tongue kiss 2:porn bed photos 3:human smoking scenes
i want use it not only detect person ,car, human smoking in bed, so i need Re-parameterization?
question Q1: can i get some suggestion about my method is correct?
Q2:how can i use yolo world to do prompt?![image](https://github.com/AILab-CVC/YOLO-World/assets/16251955/5fbefd8b-ce97-484e-8b9c-837dbdc6bc53)
Q3:how can i get Pseudo label(bboxes)by glip use this github-rep?![image](https://github.com/AILab-CVC/YOLO-World/assets/16251955/f5e2626c-aea8-490c-a03e-c2005719fd0a)
Q4:how can i do A.1. Re-parameterization for RepVL-PAN use ultralytics?![image](https://github.com/AILab-CVC/YOLO-World/assets/16251955/482423a5-f3be-43af-8efc-7627f658df4d)
thanks a lot, yolo world let my study easy~