Skip to content

Commit d22575c

Browse files
myownskyW7hellock
myownskyW7
authored and
hellock
committed
update Guided Anchoring benchmarks (open-mmlab#740)
1 parent a685729 commit d22575c

File tree

2 files changed

+23
-20
lines changed

2 files changed

+23
-20
lines changed

‎configs/guided_anchoring/README.md‎

Lines changed: 19 additions & 19 deletions
Original file line numberDiff line numberDiff line change
@@ -17,25 +17,25 @@ We provide config files to reproduce the results in the CVPR 2019 paper for [Reg
1717

1818
The results on COCO 2017 val is shown in the below table. (results on test-dev are usually slightly higher than val).
1919

20-
| Method | Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | AR 1000 | Download |
21-
| :----: | :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :-----: | :-------------------------------------------------------------------------------------------------------------------------------------------: |
22-
| GA-RPN | R-50-FPN | caffe | 1x | 5.0 | 0.55 | 13.3 | 68.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_rpn_r50_caffe_fpn_1x_20190513-95e91886.pth) |
23-
| GA-RPN | R-101-FPN | caffe | 1x | - | - | - | 69.6 | - |
24-
| GA-RPN | X-101-32x4d-FPN | pytorch | 1x | - | - | - | 70.0 | - |
25-
| GA-RPN | X-101-64x4d-FPN | pytorch | 1x | - | - | - | 70.5 | - |
26-
27-
28-
| Method | Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
29-
| :------------: | :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :-------------------------------------------------------------------------------------------------------------------------------------------------: |
30-
| GA-Fast RCNN | R-50-FPN | caffe | 1x | 3.3 | 0.23 | 14.9 | 39.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_fast_r50_caffe_fpn_1x_20190513-c5af9f8b.pth) |
31-
| GA-Faster RCNN | R-50-FPN | caffe | 1x | 5.1 | 0.64 | 9.6 | 39.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_faster_r50_caffe_fpn_1x_20190513-a52b31fa.pth) |
32-
| GA-Faster RCNN | R-101-FPN | caffe | 1x | - | - | - | 41.5 | - |
33-
| GA-Faster RCNN | X-101-32x4d-FPN | pytorch | 1x | - | - | - | 42.9 | - |
34-
| GA-Faster RCNN | X-101-64x4d-FPN | pytorch | 1x | - | - | - | 43.9 | - |
35-
| GA-RetinaNet | R-50-FPN | caffe | 1x | 3.2 | 0.50 | 10.7 | 37.0 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x_20190513-29905101.pth) |
36-
| GA-RetinaNet | R-101-FPN | caffe | 1x | - | - | - | 38.9 | - |
37-
| GA-RetinaNet | X-101-32x4d-FPN | pytorch | 1x | - | - | - | 40.3 | - |
38-
| GA-RetinaNet | X-101-64x4d-FPN | pytorch | 1x | - | - | - | 40.8 | - |
20+
| Method | Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | AR 1000 | Download |
21+
| :----: | :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :-----: | :--------------------------------------------------------------------------------------------------------------------------------------------: |
22+
| GA-RPN | R-50-FPN | caffe | 1x | 5.0 | 0.55 | 13.3 | 68.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_rpn_r50_caffe_fpn_1x_20190513-95e91886.pth) |
23+
| GA-RPN | R-101-FPN | caffe | 1x | 7.1 | 0.66 | 9.8 | 69.6 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_rpn_r101_caffe_fpn_1x_20190523-91e0b817.pth) |
24+
| GA-RPN | X-101-32x4d-FPN | pytorch | 1x | 8.5 | 0.88 | 8.5 | 70.0 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_rpn_x101_32x4d_fpn_1x_20190523-a60df28c.pth) |
25+
| GA-RPN | X-101-64x4d-FPN | pytorch | 1x | 11.4 | 1.24 | 6.5 | 70.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_rpn_x101_64x4d_fpn_1x_20190523-9f2449ba.pth) |
26+
27+
28+
| Method | Backbone | Style | Lr schd | Mem (GB) | Train time (s/iter) | Inf time (fps) | box AP | Download |
29+
| :------------: | :-------------: | :-----: | :-----: | :------: | :-----------------: | :------------: | :----: | :--------------------------------------------------------------------------------------------------------------------------------------------------: |
30+
| GA-Fast RCNN | R-50-FPN | caffe | 1x | 3.3 | 0.23 | 14.9 | 39.5 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_fast_r50_caffe_fpn_1x_20190513-c5af9f8b.pth) |
31+
| GA-Faster RCNN | R-50-FPN | caffe | 1x | 5.1 | 0.64 | 9.6 | 39.9 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_faster_r50_caffe_fpn_1x_20190513-a52b31fa.pth) |
32+
| GA-Faster RCNN | R-101-FPN | caffe | 1x | 7.3 | 0.75 | 8.0 | 41.5 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_faster_r101_caffe_fpn_1x_20190523-9a711ec5.pth) |
33+
| GA-Faster RCNN | X-101-32x4d-FPN | pytorch | 1x | 8.7 | 0.97 | 7.1 | 42.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_faster_x101_32x4d_fpn_1x_20190523-8dc3e59a.pth) |
34+
| GA-Faster RCNN | X-101-64x4d-FPN | pytorch | 1x | 11.6 | 1.33 | 5.7 | 43.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_faster_x101_64x4d_fpn_1x_20190523-a8589c97.pth) |
35+
| GA-RetinaNet | R-50-FPN | caffe | 1x | 3.2 | 0.50 | 10.7 | 37.0 | [model](https://s3.ap-northeast-2.amazonaws.com/open-mmlab/mmdetection/models/guided_anchoring/ga_retinanet_r50_caffe_fpn_1x_20190513-29905101.pth) |
36+
| GA-RetinaNet | R-101-FPN | caffe | 1x | 5.3 | 0.63 | 8.5 | 38.9 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_retinanet_r101_caffe_fpn_1x_20190523-792ad63d.pth) |
37+
| GA-RetinaNet | X-101-32x4d-FPN | pytorch | 1x | 6.7 | 0.87 | 7.5 | 40.3 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_retinanet_x101_32x4d_fpn_1x_20190523-4ec3f13c.pth) |
38+
| GA-RetinaNet | X-101-64x4d-FPN | pytorch | 1x | 9.6 | 1.22 | 5.8 | 40.8 | [model](https://open-mmlab.s3.ap-northeast-2.amazonaws.com/mmdetection/models/guided_anchoring/ga_retinanet_x101_64x4d_fpn_1x_20190523-013d1913.pth) |
3939

4040

4141

‎mmdet/models/anchor_heads/guided_anchor_head.py‎

Lines changed: 4 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -114,7 +114,10 @@ def __init__(self,
114114
gamma=2.0,
115115
alpha=0.25,
116116
loss_weight=1.0),
117-
loss_shape=dict(type='IoULoss', beta=0.2, loss_weight=1.0),
117+
loss_shape=dict(type='IoULoss',
118+
style='bounded',
119+
beta=0.2,
120+
loss_weight=1.0),
118121
loss_cls=dict(type='CrossEntropyLoss',
119122
use_sigmoid=True,
120123
loss_weight=1.0),

0 commit comments

Comments
 (0)