33 lines
959 B
YAML
33 lines
959 B
YAML
Collections:
|
|
- Name: YOLOF
|
|
Metadata:
|
|
Training Data: COCO
|
|
Training Techniques:
|
|
- SGD with Momentum
|
|
- Weight Decay
|
|
Training Resources: 8x V100 GPUs
|
|
Architecture:
|
|
- Dilated Encoder
|
|
- ResNet
|
|
Paper:
|
|
URL: https://arxiv.org/abs/2103.09460
|
|
Title: 'You Only Look One-level Feature'
|
|
README: configs/yolof/README.md
|
|
Code:
|
|
URL: https://github.com/open-mmlab/mmdetection/blob/v2.12.0/mmdet/models/detectors/yolof.py#L6
|
|
Version: v2.12.0
|
|
|
|
Models:
|
|
- Name: yolof_r50_c5_8x8_1x_coco
|
|
In Collection: YOLOF
|
|
Config: configs/yolof/yolof_r50_c5_8x8_1x_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 8.3
|
|
Epochs: 12
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 37.5
|
|
Weights: https://download.openmmlab.com/mmdetection/v2.0/yolof/yolof_r50_c5_8x8_1x_coco/yolof_r50_c5_8x8_1x_coco_20210425_024427-8e864411.pth
|