From 46cc0cb03c3a600661a8ff4f50035b6c6aaad4f9 Mon Sep 17 00:00:00 2001 From: Kai Chen <chenkaidev@gmail.com> Date: Tue, 25 Jun 2019 16:59:09 +0800 Subject: [PATCH] Add GHM benchmark (#776) * add benchmarks * add ghm x101-64x4d * fix a model url * add training and inference speed --- configs/ghm/README.md | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/configs/ghm/README.md b/configs/ghm/README.md index 6596595..cf720ee 100644 --- a/configs/ghm/README.md +++ b/configs/ghm/README.md @@ -13,4 +13,9 @@ ## Results and Models -To be benchmarked. \ No newline at end of file +| Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download | +| :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :------: | +| R-50-FPN | pytorch | 1x | 3.9 | 0.500 | 9.4 | 36.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_r50_fpn_1x_20190608-b9aa5862.pth) | +| R-101-FPN | pytorch | 1x | 5.8 | 0.625 | 8.5 | 39.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_r101_fpn_1x_20190608-b885b74a.pth) | +| X-101-32x4d-FPN | pytorch | 1x | 7.0 | 0.818 | 7.6 | 40.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_x101_32x4d_fpn_1x_20190608-ed295d22.pth) | +| X-101-64x4d-FPN | pytorch | 1x | 9.9 | 1.191 | 6.1 | 41.6 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/ghm/retinanet_ghm_x101_64x4d_fpn_1x_20190608-7f2037ce.pth) | \ No newline at end of file -- GitLab