hustvl
/
yolos-small
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Niels Rogge 2022-05-02 12:57:41 +00:00 committed by huggingface-web
parent 64cbfbc5d5
commit 79465d48c5
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -15,13 +15,13 @@ widget:
# YOLOS (small-sized) model
YOLOS model trained on COCO 2017 object detection (118k annotated images). It was introduced in the paper [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://arxiv.org/abs/2106.00666) by Fang et al. and first released in [this repository](https://github.com/hustvl/YOLOS).
YOLOS model fine-tuned on COCO 2017 object detection (118k annotated images). It was introduced in the paper [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://arxiv.org/abs/2106.00666) by Fang et al. and first released in [this repository](https://github.com/hustvl/YOLOS).
Disclaimer: The team releasing YOLOS did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN.
YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN).
The model is trained using a "bipartite matching loss": one compares the predicted classes + bounding boxes of each of the N = 100 object queries to the ground truth annotations, padded up to the same length N (so if an image only contains 4 objects, 96 annotations will just have a "no object" as class and "no bounding box" as bounding box). The Hungarian matching algorithm is used to create an optimal one-to-one mapping between each of the N queries and each of the N annotations. Next, standard cross-entropy (for the classes) and a linear combination of the L1 and generalized IoU loss (for the bounding boxes) are used to optimize the parameters of the model.