stevengrove
initial commit
186701e
raw
history blame
3.05 kB
Collections:
- Name: YOLOv7
Metadata:
Training Data: COCO
Training Techniques:
- SGD with Nesterov
- Weight Decay
- AMP
- Synchronize BN
Training Resources: 8x A100 GPUs
Architecture:
- EELAN
- PAFPN
- RepVGG
Paper:
URL: https://arxiv.org/abs/2207.02696
Title: 'YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors'
README: configs/yolov7/README.md
Code:
URL: https://github.com/open-mmlab/mmyolo/blob/v0.0.1/mmyolo/models/detectors/yolo_detector.py#L12
Version: v0.0.1
Models:
- Name: yolov7_tiny_syncbn_fast_8x16b-300e_coco
In Collection: YOLOv7
Config: configs/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco.py
Metadata:
Training Memory (GB): 2.7
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 37.5
Weights: https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_tiny_syncbn_fast_8x16b-300e_coco/yolov7_tiny_syncbn_fast_8x16b-300e_coco_20221126_102719-0ee5bbdf.pth
- Name: yolov7_l_syncbn_fast_8x16b-300e_coco
In Collection: YOLOv7
Config: configs/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco.py
Metadata:
Training Memory (GB): 10.3
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 50.9
Weights: https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_l_syncbn_fast_8x16b-300e_coco/yolov7_l_syncbn_fast_8x16b-300e_coco_20221123_023601-8113c0eb.pth
- Name: yolov7_x_syncbn_fast_8x16b-300e_coco
In Collection: YOLOv7
Config: configs/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco.py
Metadata:
Training Memory (GB): 13.7
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 52.8
Weights: https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_x_syncbn_fast_8x16b-300e_coco/yolov7_x_syncbn_fast_8x16b-300e_coco_20221124_215331-ef949a68.pth
- Name: yolov7_w-p6_syncbn_fast_8x16b-300e_coco
In Collection: YOLOv7
Config: configs/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco.py
Metadata:
Training Memory (GB): 27.0
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 54.1
Weights: https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_w-p6_syncbn_fast_8x16b-300e_coco/yolov7_w-p6_syncbn_fast_8x16b-300e_coco_20221123_053031-a68ef9d2.pth
- Name: yolov7_e-p6_syncbn_fast_8x16b-300e_coco
In Collection: YOLOv7
Config: configs/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco.py
Metadata:
Training Memory (GB): 42.5
Epochs: 300
Results:
- Task: Object Detection
Dataset: COCO
Metrics:
box AP: 55.1
Weights: https://download.openmmlab.com/mmyolo/v0/yolov7/yolov7_e-p6_syncbn_fast_8x16b-300e_coco/yolov7_e-p6_syncbn_fast_8x16b-300e_coco_20221126_102636-34425033.pth