Architecture | Convolution, Corner Pooling, Stacked Hourglass Network, 1x1 Convolution, RoIAlign |
---|---|
Batch Size | 16 x 6 |
SHOW MORE |
[ALGORITHM]
@InProceedings{Dong_2020_CVPR,
author = {Dong, Zhiwei and Li, Guoxuan and Liao, Yue and Wang, Fei and Ren, Pengju and Qian, Chen},
title = {CentripetalNet: Pursuing High-Quality Keypoint Pairs for Object Detection},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}
Backbone | Batch Size | Step/Total Epochs | Mem (GB) | Inf time (fps) | box AP | Config | Download |
---|---|---|---|---|---|---|---|
HourglassNet-104 | 16 x 6 | 190/210 | 16.7 | 3.7 | 44.8 | config | model | log |
Note:
flip=True
.
BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
---|---|---|---|---|
COCO minival | CentripetalNet (HourglassNet-104, bs=16 x 6) | box AP | 44.8 | # 28 |