Hello Hugging Face community,
These days I was researching the YOLO series and applying them to autonomous driving tasks. When I heard about Hugging Face, I got immediately fascinated by the Space and web APP platform provided by Hugging Face. Then I came up with an idea that I want to try this stuff and do something interesting to me.
I finished finetuning a YOLOS model for traffic object detection tasks and building a small demo app based on this model. It’s so cool and so convenient. I will keep maintaining this mini-project and plan to make it able to achieve multi-task panoptic driving perception just like YOLOP. (Like a multi-tass head with transformer)
Project: YOLOS Traffic Object detection - a Hugging Face Space by PierreSHI
Any suggestions?