mirror of https://github.com/open-mmlab/mmyolo.git
47 lines
1.4 KiB
YAML
47 lines
1.4 KiB
YAML
Collections:
|
|
- Name: YOLOX
|
|
Metadata:
|
|
Training Data: COCO
|
|
Training Techniques:
|
|
- SGD with Nesterov
|
|
- Weight Decay
|
|
- Cosine Annealing Lr Updater
|
|
Training Resources: 8x A100 GPUs
|
|
Architecture:
|
|
- CSPDarkNet
|
|
- PAFPN
|
|
Paper:
|
|
URL: https://arxiv.org/abs/2107.08430
|
|
Title: 'YOLOX: Exceeding YOLO Series in 2021'
|
|
README: configs/yolox/README.md
|
|
Code:
|
|
URL: https://github.com/open-mmlab/mmyolo/blob/v0.1.0/mmyolo/models/detectors/yolo_detector.py#L12
|
|
Version: v0.1.0
|
|
|
|
|
|
Models:
|
|
- Name: yolox_tiny_8xb8-300e_coco
|
|
In Collection: YOLOX
|
|
Config: configs/yolox/yolox_tiny_8xb8-300e_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 2.8
|
|
Epochs: 300
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 32.7
|
|
Weights: https://download.openmmlab.com/mmyolo/v0/yolox/yolox_tiny_8xb8-300e_coco/yolox_tiny_8xb8-300e_coco_20220919_090908-0e40a6fc.pth
|
|
- Name: yolox_s_8xb8-300e_coco
|
|
In Collection: YOLOX
|
|
Config: configs/yolox/yolox_s_8xb8-300e_coco.py
|
|
Metadata:
|
|
Training Memory (GB): 5.6
|
|
Epochs: 300
|
|
Results:
|
|
- Task: Object Detection
|
|
Dataset: COCO
|
|
Metrics:
|
|
box AP: 40.8
|
|
Weights: https://download.openmmlab.com/mmyolo/v0/yolox/yolox_s_8xb8-300e_coco/yolox_s_8xb8-300e_coco_20220917_030738-d7e60cb2.pth
|