From 6050186056dcf8f50cc8115a22bfeb1fa5b56063 Mon Sep 17 00:00:00 2001 From: Cao Yuhang <yhcao6@gmail.com> Date: Fri, 24 May 2019 00:11:41 +0800 Subject: [PATCH] Add more FCOS benchmark (#689) * add fcos_r50_bn, fcos_r50_2x_no_ms benchmark * split table by ms-training * adjust table * add r101 2x without ms train performance --- configs/fcos/README.md | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/configs/fcos/README.md b/configs/fcos/README.md index 6781fa5..fe78977 100644 --- a/configs/fcos/README.md +++ b/configs/fcos/README.md @@ -13,13 +13,21 @@ ## Results and Models -| Backbone | Style | Multi-scale training | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download | -|:---------:|:-------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:| -| R-50-FPN | caffe | N | 1x | 6.9 | 0.396 | 13.6 | 36.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu_20190516-9f253a93.pth) | -| R-50-FPN | caffe | Y | 2x | - | - | - | 38.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_r50_caffe_fpn_gn_2x_4gpu_20190516-f7329d80.pth) | -| R-101-FPN | caffe | N | 1x | 10.4 | 0.558 | 11.6 | 39.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r101_caffe_fpn_gn_1x_4gpu_20190516-e4889733.pth) | -| R-101-FPN | caffe | Y | 2x | - | - | - | 40.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu_20190516-42e6f62d.pth) | -| X-101-64x4d-FPN | caffe | Y |2x | 9.7 | 0.892 | 7.0 | 42.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x_20190516-a36c0872.pth) | +| Backbone | Style | GN | MS train | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download | +|:---------:|:-------:|:-------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:| +| R-50 | caffe | N | N | 1x | 5.5 | 0.373 | 13.7 | 35.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_caffe_fpn_1x_4gpu_20190516-a7cac5ff.pth) | +| R-50 | caffe | Y | N | 1x | 6.9 | 0.396 | 13.6 | 36.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_caffe_fpn_gn_1x_4gpu_20190516-9f253a93.pth) | +| R-50 | caffe | Y | N | 2x | - | - | - | 36.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r50_caffe_fpn_gn_2x_4gpu_20190516_-93484354.pth) | +| R-101 | caffe | Y | N | 1x | 10.4 | 0.558 | 11.6 | 39.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r101_caffe_fpn_gn_1x_4gpu_20190516-e4889733.pth) | +| R-101 | caffe | Y | N | 2x | - | - | - | 39.1 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_r101_caffe_fpn_gn_2x_4gpu_20190516-c03af97b.pth) | + + +| Backbone | Style | GN | MS train | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download | +|:---------:|:-------:|:-------:|:-------:|:-------:|:--------:|:-------------------:|:--------------:|:------:|:--------:| +| R-50 | caffe | Y | Y | 2x | - | - | - | 38.7 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_r50_caffe_fpn_gn_2x_4gpu_20190516-f7329d80.pth) | +| R-101 | caffe | Y | Y | 2x | - | - | - | 40.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_r101_caffe_fpn_gn_2x_4gpu_20190516-42e6f62d.pth) | +| X-101 | caffe | Y | Y | 2x | 9.7 | 0.892 | 7.0 | 42.8 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/fcos/fcos_mstrain_640_800_x101_64x4d_fpn_gn_2x_20190516-a36c0872.pth) | **Notes:** - To be consistent with the author's implementation, we use 4 GPUs with 4 images/GPU for R-50 and R-101 models, and 8 GPUs with 2 image/GPU for X-101 models. +- The X-101 backbone is X-101-64x4d. -- GitLab