Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
cc 89de797879 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
topformer_base_ade20k_512x512_160k.yml | 1 year ago | |
topformer_small_ade20k_512x512_160k.yml | 1 year ago | |
topformer_tiny_ade20k_512x512_160k.yml | 1 year ago |
Zhang, Wenqiang, Zilong Huang, Guozhong Luo, Tao Chen, Xinggang Wang, Wenyu Liu, Gang Yu,and Chunhua Shen. "TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12083-12093. 2022.
Model | Backbone | Resolution | Training Iters | mIoU | mIoU (flip) | mIoU (ms+flip) | Links |
---|---|---|---|---|---|---|---|
TopFormer-Base | topformer | 512x512 | 160000 | 38.28% | 38.59% | - | model | log | vdl |
TopFormer-Small | topformer | 512x512 | 160000 | 35.60% | 35.83% | - | model | log | vdl |
TopFormer-Tiny | topformer | 512x512 | 160000 | 32.49% | 32.75% | - | model | log | vdl |
Note that, the input resulution of TopFormer should be a multiple of 32.
飞桨高性能图像分割开发套件,端到端完成从训练到部署的全流程图像分割应用。
https://github.com/PaddlePaddle/PaddleSeg
Python Markdown Text Shell 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》