OpenMMLab Detection Toolbox and Benchmark https://mmdetection.readthedocs.io/
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 

147 lines
4.9 KiB

Collections:
- Name: RetinaNet
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Momentum
- Weight Decay
Training Resources: 8x NVIDIA V100 GPUs
Architecture:
- Focal Loss
- FPN
- ResNet
Paper: https://arxiv.org/abs/1708.02002
README: configs/retinanet/README.md
Models:
- Name: retinanet_r50_caffe_fpn_1x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_r50_caffe_fpn_1x_coco.py
Metadata:
Training Memory (GB): 3.5
inference time (s/im): 0.05376
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 36.3
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r50_caffe_fpn_1x_coco/retinanet_r50_caffe_fpn_1x_coco_20200531-f11027c5.pth
- Name: retinanet_r50_fpn_1x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_r50_fpn_1x_coco.py
Metadata:
Training Memory (GB): 3.8
inference time (s/im): 0.05263
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 36.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r50_fpn_1x_coco/retinanet_r50_fpn_1x_coco_20200130-c2398f9e.pth
- Name: retinanet_r50_fpn_2x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_r50_fpn_2x_coco.py
Metadata:
Epochs: 24
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 37.4
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r50_fpn_2x_coco/retinanet_r50_fpn_2x_coco_20200131-fdb43119.pth
- Name: retinanet_r101_caffe_fpn_1x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_r101_caffe_fpn_1x_coco.py
Metadata:
Training Memory (GB): 5.5
inference time (s/im): 0.06803
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 38.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r101_caffe_fpn_1x_coco/retinanet_r101_caffe_fpn_1x_coco_20200531-b428fa0f.pth
- Name: retinanet_r101_fpn_1x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_r101_fpn_1x_coco.py
Metadata:
Training Memory (GB): 5.7
inference time (s/im): 0.06667
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 38.5
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r101_fpn_1x_coco/retinanet_r101_fpn_1x_coco_20200130-7a93545f.pth
- Name: retinanet_r101_fpn_2x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_r101_fpn_2x_coco.py
Metadata:
Epochs: 24
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 38.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r101_fpn_2x_coco/retinanet_r101_fpn_2x_coco_20200131-5560aee8.pth
- Name: retinanet_x101_32x4d_fpn_1x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_x101_32x4d_fpn_1x_coco.py
Metadata:
Training Memory (GB): 7.0
inference time (s/im): 0.08264
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 39.9
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_x101_32x4d_fpn_1x_coco/retinanet_x101_32x4d_fpn_1x_coco_20200130-5c8b7ec4.pth
- Name: retinanet_x101_32x4d_fpn_2x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_x101_32x4d_fpn_2x_coco.py
Metadata:
Epochs: 24
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.1
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_x101_32x4d_fpn_2x_coco/retinanet_x101_32x4d_fpn_2x_coco_20200131-237fc5e1.pth
- Name: retinanet_x101_64x4d_fpn_1x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_x101_64x4d_fpn_1x_coco.py
Metadata:
Training Memory (GB): 10.0
inference time (s/im): 0.11494
Epochs: 12
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 41.0
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_x101_64x4d_fpn_1x_coco/retinanet_x101_64x4d_fpn_1x_coco_20200130-366f5af1.pth
- Name: retinanet_x101_64x4d_fpn_2x_coco
In Collection: RetinaNet
Config: configs/retinanet/retinanet_x101_64x4d_fpn_2x_coco.py
Metadata:
Epochs: 24
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 40.8
Weights: https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_x101_64x4d_fpn_2x_coco/retinanet_x101_64x4d_fpn_2x_coco_20200131-bca068ab.pth