| Collections: | |
| - Name: GHM | |
| Metadata: | |
| Training Data: COCO | |
| Training Techniques: | |
| - SGD with Momentum | |
| - Weight Decay | |
| Training Resources: 8x V100 GPUs | |
| Architecture: | |
| - GHM-C | |
| - GHM-R | |
| - FPN | |
| - ResNet | |
| Paper: | |
| URL: https://arxiv.org/abs/1811.05181 | |
| Title: 'Gradient Harmonized Single-stage Detector' | |
| README: configs/ghm/README.md | |
| Code: | |
| URL: https://github.com/open-mmlab/mmdetection/blob/v2.0.0/mmdet/models/losses/ghm_loss.py#L21 | |
| Version: v2.0.0 | |
| Models: | |
| - Name: retinanet_r50_fpn_ghm-1x_coco | |
| In Collection: GHM | |
| Config: configs/ghm/retinanet_r50_fpn_ghm-1x_coco.py | |
| Metadata: | |
| Training Memory (GB): 4.0 | |
| inference time (ms/im): | |
| - value: 303.03 | |
| hardware: V100 | |
| backend: PyTorch | |
| batch size: 1 | |
| mode: FP32 | |
| resolution: (800, 1333) | |
| Epochs: 12 | |
| Results: | |
| - Task: Object Detection | |
| Dataset: COCO | |
| Metrics: | |
| box AP: 37.0 | |
| Weights: https://download.openmmlab.com/mmdetection/v2.0/ghm/retinanet_ghm_r50_fpn_1x_coco/retinanet_ghm_r50_fpn_1x_coco_20200130-a437fda3.pth | |
| - Name: retinanet_r101_fpn_ghm-1x_coco | |
| In Collection: GHM | |
| Config: configs/ghm/retinanet_r101_fpn_ghm-1x_coco.py | |
| Metadata: | |
| Training Memory (GB): 6.0 | |
| inference time (ms/im): | |
| - value: 227.27 | |
| hardware: V100 | |
| backend: PyTorch | |
| batch size: 1 | |
| mode: FP32 | |
| resolution: (800, 1333) | |
| Epochs: 12 | |
| Results: | |
| - Task: Object Detection | |
| Dataset: COCO | |
| Metrics: | |
| box AP: 39.1 | |
| Weights: https://download.openmmlab.com/mmdetection/v2.0/ghm/retinanet_ghm_r101_fpn_1x_coco/retinanet_ghm_r101_fpn_1x_coco_20200130-c148ee8f.pth | |
| - Name: retinanet_x101-32x4d_fpn_ghm-1x_coco | |
| In Collection: GHM | |
| Config: configs/ghm/retinanet_x101-32x4d_fpn_ghm-1x_coco.py | |
| Metadata: | |
| Training Memory (GB): 7.2 | |
| inference time (ms/im): | |
| - value: 196.08 | |
| hardware: V100 | |
| backend: PyTorch | |
| batch size: 1 | |
| mode: FP32 | |
| resolution: (800, 1333) | |
| Epochs: 12 | |
| Results: | |
| - Task: Object Detection | |
| Dataset: COCO | |
| Metrics: | |
| box AP: 40.7 | |
| Weights: https://download.openmmlab.com/mmdetection/v2.0/ghm/retinanet_ghm_x101_32x4d_fpn_1x_coco/retinanet_ghm_x101_32x4d_fpn_1x_coco_20200131-e4333bd0.pth | |
| - Name: retinanet_x101-64x4d_fpn_ghm-1x_coco | |
| In Collection: GHM | |
| Config: configs/ghm/retinanet_x101-64x4d_fpn_ghm-1x_coco.py | |
| Metadata: | |
| Training Memory (GB): 10.3 | |
| inference time (ms/im): | |
| - value: 192.31 | |
| hardware: V100 | |
| backend: PyTorch | |
| batch size: 1 | |
| mode: FP32 | |
| resolution: (800, 1333) | |
| Epochs: 12 | |
| Results: | |
| - Task: Object Detection | |
| Dataset: COCO | |
| Metrics: | |
| box AP: 41.4 | |
| Weights: https://download.openmmlab.com/mmdetection/v2.0/ghm/retinanet_ghm_x101_64x4d_fpn_1x_coco/retinanet_ghm_x101_64x4d_fpn_1x_coco_20200131-dd381cef.pth | |