Skip to content

Commit 1eb94a5

Browse files
BIGWangYuDongRangiLyu
authored and
ZwwWayne
committed
[Fix] update metafile (#6717)
* [Fix] fix metafile and config file * minior fix * Update configs/seesaw_loss/metafile.yml Co-authored-by: RangiLyu <lyuchqi@gmail.com> Co-authored-by: RangiLyu <lyuchqi@gmail.com>
1 parent bd1276e commit 1eb94a5

File tree

2 files changed

+258
-0
lines changed

2 files changed

+258
-0
lines changed

‎configs/carafe/metafile.yml

+55
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,55 @@
1+
Collections:
2+
- Name: CARAFE
3+
Metadata:
4+
Training Data: COCO
5+
Training Techniques:
6+
- SGD with Momentum
7+
- Weight Decay
8+
Training Resources: 8x V100 GPUs
9+
Architecture:
10+
- RPN
11+
- FPN_CARAFE
12+
- ResNet
13+
- RoIPool
14+
Paper:
15+
URL: https://arxiv.org/abs/1905.02188
16+
Title: 'CARAFE: Content-Aware ReAssembly of FEatures'
17+
README: configs/carafe/README.md
18+
Code:
19+
URL: https://github.com/open-mmlab/mmdetection/blob/v2.12.0/mmdet/models/necks/fpn_carafe.py#L11
20+
Version: v2.12.0
21+
22+
Models:
23+
- Name: faster_rcnn_r50_fpn_carafe_1x_coco
24+
In Collection: CARAFE
25+
Config: configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py
26+
Metadata:
27+
Training Memory (GB): 4.26
28+
Epochs: 12
29+
Results:
30+
- Task: Object Detection
31+
Dataset: COCO
32+
Metrics:
33+
box AP: 38.6
34+
- Task: Instance Segmentation
35+
Dataset: COCO
36+
Metrics:
37+
mask AP: 38.6
38+
Weights: https://download.openmmlab.com/mmdetection/v2.0/carafe/faster_rcnn_r50_fpn_carafe_1x_coco/faster_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.386_20200504_175733-385a75b7.pth
39+
40+
- Name: mask_rcnn_r50_fpn_carafe_1x_coco
41+
In Collection: CARAFE
42+
Config: configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py
43+
Metadata:
44+
Training Memory (GB): 4.31
45+
Epochs: 12
46+
Results:
47+
- Task: Object Detection
48+
Dataset: COCO
49+
Metrics:
50+
box AP: 39.3
51+
- Task: Instance Segmentation
52+
Dataset: COCO
53+
Metrics:
54+
mask AP: 35.6
55+
Weights: https://download.openmmlab.com/mmdetection/v2.0/carafe/mask_rcnn_r50_fpn_carafe_1x_coco/mask_rcnn_r50_fpn_carafe_1x_coco_bbox_mAP-0.393__segm_mAP-0.358_20200503_135957-8687f195.pth

‎configs/seesaw_loss/metafile.yml

+203
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,203 @@
1+
Collections:
2+
- Name: Seesaw Loss
3+
Metadata:
4+
Training Data: LVIS
5+
Training Techniques:
6+
- SGD with Momentum
7+
- Weight Decay
8+
Training Resources: 8x V100 GPUs
9+
Architecture:
10+
- Softmax
11+
- RPN
12+
- Convolution
13+
- Dense Connections
14+
- FPN
15+
- ResNet
16+
- RoIAlign
17+
- Seesaw Loss
18+
Paper:
19+
URL: https://arxiv.org/abs/2008.10032
20+
Title: 'Seesaw Loss for Long-Tailed Instance Segmentation'
21+
README: configs/seesaw_loss/README.md
22+
23+
Models:
24+
- Name: mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1
25+
In Collection: Seesaw Loss
26+
Config: seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py
27+
Metadata:
28+
Epochs: 24
29+
Results:
30+
- Task: Object Detection
31+
Dataset: LVIS v1
32+
Metrics:
33+
box AP: 25.6
34+
- Task: Instance Segmentation
35+
Dataset: LVIS v1
36+
Metrics:
37+
mask AP: 25.0
38+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-a698dd3d.pth
39+
- Name: mask_rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
40+
In Collection: Seesaw Loss
41+
Config: seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py
42+
Metadata:
43+
Epochs: 24
44+
Results:
45+
- Task: Object Detection
46+
Dataset: LVIS v1
47+
Metrics:
48+
box AP: 25.6
49+
- Task: Instance Segmentation
50+
Dataset: LVIS v1
51+
Metrics:
52+
mask AP: 25.4
53+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-a1c11314.pth
54+
- Name: mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1
55+
In Collection: Seesaw Loss
56+
Config: seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py
57+
Metadata:
58+
Epochs: 24
59+
Results:
60+
- Task: Object Detection
61+
Dataset: LVIS v1
62+
Metrics:
63+
box AP: 27.4
64+
- Task: Instance Segmentation
65+
Dataset: LVIS v1
66+
Metrics:
67+
mask AP: 26.7
68+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-8e6e6dd5.pth
69+
- Name: mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
70+
In Collection: Seesaw Loss
71+
Config: seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py
72+
Metadata:
73+
Epochs: 24
74+
Results:
75+
- Task: Object Detection
76+
Dataset: LVIS v1
77+
Metrics:
78+
box AP: 27.2
79+
- Task: Instance Segmentation
80+
Dataset: LVIS v1
81+
Metrics:
82+
mask AP: 27.3
83+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-a0b59c42.pth
84+
- Name: mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1
85+
In Collection: Seesaw Loss
86+
Config: configs/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py
87+
Metadata:
88+
Epochs: 24
89+
Results:
90+
- Task: Object Detection
91+
Dataset: LVIS v1
92+
Metrics:
93+
box AP: 27.6
94+
- Task: Instance Segmentation
95+
Dataset: LVIS v1
96+
Metrics:
97+
mask AP: 26.4
98+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1-392a804b.pth
99+
- Name: mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
100+
In Collection: Seesaw Loss
101+
Config: configs/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py
102+
Metadata:
103+
Epochs: 24
104+
Results:
105+
- Task: Object Detection
106+
Dataset: LVIS v1
107+
Metrics:
108+
box AP: 27.6
109+
- Task: Instance Segmentation
110+
Dataset: LVIS v1
111+
Metrics:
112+
mask AP: 26.8
113+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-cd0f6a12.pth
114+
- Name: mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1
115+
In Collection: Seesaw Loss
116+
Config: configs/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py
117+
Metadata:
118+
Epochs: 24
119+
Results:
120+
- Task: Object Detection
121+
Dataset: LVIS v1
122+
Metrics:
123+
box AP: 28.9
124+
- Task: Instance Segmentation
125+
Dataset: LVIS v1
126+
Metrics:
127+
mask AP: 27.6
128+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1-e68eb464.pth
129+
- Name: mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
130+
In Collection: Seesaw Loss
131+
Config: configs/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py
132+
Metadata:
133+
Epochs: 24
134+
Results:
135+
- Task: Object Detection
136+
Dataset: LVIS v1
137+
Metrics:
138+
box AP: 28.9
139+
- Task: Instance Segmentation
140+
Dataset: LVIS v1
141+
Metrics:
142+
mask AP: 28.2
143+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-1d817139.pth
144+
- Name: cascade_mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1
145+
In Collection: Seesaw Loss
146+
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py
147+
Metadata:
148+
Epochs: 24
149+
Results:
150+
- Task: Object Detection
151+
Dataset: LVIS v1
152+
Metrics:
153+
box AP: 33.1
154+
- Task: Instance Segmentation
155+
Dataset: LVIS v1
156+
Metrics:
157+
mask AP: 29.2
158+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-71e2215e.pth
159+
- Name: cascade_mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
160+
In Collection: Seesaw Loss
161+
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py
162+
Metadata:
163+
Epochs: 24
164+
Results:
165+
- Task: Object Detection
166+
Dataset: LVIS v1
167+
Metrics:
168+
box AP: 33.0
169+
- Task: Instance Segmentation
170+
Dataset: LVIS v1
171+
Metrics:
172+
mask AP: 30.0
173+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-8b5a6745.pth
174+
- Name: cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1
175+
In Collection: Seesaw Loss
176+
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py
177+
Metadata:
178+
Epochs: 24
179+
Results:
180+
- Task: Object Detection
181+
Dataset: LVIS v1
182+
Metrics:
183+
box AP: 30.0
184+
- Task: Instance Segmentation
185+
Dataset: LVIS v1
186+
Metrics:
187+
mask AP: 29.3
188+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1-5d8ca2a4.pth
189+
- Name: cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1
190+
In Collection: Seesaw Loss
191+
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py
192+
Metadata:
193+
Epochs: 24
194+
Results:
195+
- Task: Object Detection
196+
Dataset: LVIS v1
197+
Metrics:
198+
box AP: 32.8
199+
- Task: Instance Segmentation
200+
Dataset: LVIS v1
201+
Metrics:
202+
mask AP: 30.1
203+
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1-c8551505.pth

0 commit comments

Comments
 (0)