Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Guanghua Yu a1acbce3f9 | 3 years ago | |
---|---|---|
.. | ||
_base_ | 3 years ago | |
README.md | 3 years ago | |
fcos_dcn_r50_fpn_1x_coco.yml | 3 years ago | |
fcos_r50_fpn_1x_coco.yml | 3 years ago | |
fcos_r50_fpn_multiscale_2x_coco.yml | 3 years ago |
FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free object detection framework with strong performance. We reproduced the model of the paper, and improved and optimized the accuracy of the FCOS.
Highlights:
fcos_r50_fpn_1x
on Tesla v100 with 8 GPU is only 8.5 hours.Backbone | Model | images/GPU | lr schedule | FPS | Box AP | download | config |
---|---|---|---|---|---|---|---|
ResNet50-FPN | FCOS | 2 | 1x | ---- | 39.6 | download | config |
ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | download | config |
ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 41.8 | download | config |
Notes:
mAP(IoU=0.5:0.95)
.@inproceedings{tian2019fcos,
title = {{FCOS}: Fully Convolutional One-Stage Object Detection},
author = {Tian, Zhi and Shen, Chunhua and Chen, Hao and He, Tong},
booktitle = {Proc. Int. Conf. Computer Vision (ICCV)},
year = {2019}
}
PaddleDetection
Python Jupyter Notebook Markdown C++ Java other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》