-
Notifications
You must be signed in to change notification settings - Fork 9.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* [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>
- Loading branch information
1 parent
7277a25
commit d5f40aa
Showing
2 changed files
with
258 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,55 @@ | ||
Collections: | ||
- Name: CARAFE | ||
Metadata: | ||
Training Data: COCO | ||
Training Techniques: | ||
- SGD with Momentum | ||
- Weight Decay | ||
Training Resources: 8x V100 GPUs | ||
Architecture: | ||
- RPN | ||
- FPN_CARAFE | ||
- ResNet | ||
- RoIPool | ||
Paper: | ||
URL: https://arxiv.org/abs/1905.02188 | ||
Title: 'CARAFE: Content-Aware ReAssembly of FEatures' | ||
README: configs/carafe/README.md | ||
Code: | ||
URL: https://github.com/open-mmlab/mmdetection/blob/v2.12.0/mmdet/models/necks/fpn_carafe.py#L11 | ||
Version: v2.12.0 | ||
|
||
Models: | ||
- Name: faster_rcnn_r50_fpn_carafe_1x_coco | ||
In Collection: CARAFE | ||
Config: configs/carafe/faster_rcnn_r50_fpn_carafe_1x_coco.py | ||
Metadata: | ||
Training Memory (GB): 4.26 | ||
Epochs: 12 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: COCO | ||
Metrics: | ||
box AP: 38.6 | ||
- Task: Instance Segmentation | ||
Dataset: COCO | ||
Metrics: | ||
mask AP: 38.6 | ||
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 | ||
|
||
- Name: mask_rcnn_r50_fpn_carafe_1x_coco | ||
In Collection: CARAFE | ||
Config: configs/carafe/mask_rcnn_r50_fpn_carafe_1x_coco.py | ||
Metadata: | ||
Training Memory (GB): 4.31 | ||
Epochs: 12 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: COCO | ||
Metrics: | ||
box AP: 39.3 | ||
- Task: Instance Segmentation | ||
Dataset: COCO | ||
Metrics: | ||
mask AP: 35.6 | ||
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 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,203 @@ | ||
Collections: | ||
- Name: Seesaw Loss | ||
Metadata: | ||
Training Data: LVIS | ||
Training Techniques: | ||
- SGD with Momentum | ||
- Weight Decay | ||
Training Resources: 8x V100 GPUs | ||
Architecture: | ||
- Softmax | ||
- RPN | ||
- Convolution | ||
- Dense Connections | ||
- FPN | ||
- ResNet | ||
- RoIAlign | ||
- Seesaw Loss | ||
Paper: | ||
URL: https://arxiv.org/abs/2008.10032 | ||
Title: 'Seesaw Loss for Long-Tailed Instance Segmentation' | ||
README: configs/seesaw_loss/README.md | ||
|
||
Models: | ||
- Name: mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 25.6 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 25.0 | ||
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-a698dd3d.pth | ||
- Name: mask_rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: seesaw_loss/mask_rcnn_r50_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 25.6 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 25.4 | ||
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 | ||
- Name: mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 27.4 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 26.7 | ||
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-8e6e6dd5.pth | ||
- Name: mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: seesaw_loss/mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 27.2 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 27.3 | ||
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 | ||
- Name: mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 27.6 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 26.4 | ||
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1-392a804b.pth | ||
- Name: mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/mask_rcnn_r50_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 27.6 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 26.8 | ||
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 | ||
- Name: mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 28.9 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 27.6 | ||
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1-e68eb464.pth | ||
- Name: mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 28.9 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 28.2 | ||
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 | ||
- Name: cascade_mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 33.1 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 29.2 | ||
Weights: https://download.openmmlab.com/mmdetection/v2.0/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_mstrain_2x_lvis_v1-71e2215e.pth | ||
- Name: cascade_mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_random_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 33.0 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 30.0 | ||
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 | ||
- Name: cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 30.0 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 29.3 | ||
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 | ||
- Name: cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1 | ||
In Collection: Seesaw Loss | ||
Config: configs/seesaw_loss/cascade_mask_rcnn_r101_fpn_sample1e-3_seesaw_loss_normed_mask_mstrain_2x_lvis_v1.py | ||
Metadata: | ||
Epochs: 24 | ||
Results: | ||
- Task: Object Detection | ||
Dataset: LVIS v1 | ||
Metrics: | ||
box AP: 32.8 | ||
- Task: Instance Segmentation | ||
Dataset: LVIS v1 | ||
Metrics: | ||
mask AP: 30.1 | ||
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 |