未验证 提交 26c2a4f2 编写于 作者: K Kaipeng Deng 提交者: GitHub

fix README for yolov3 (#930)

* fix README for yolov3

* add NOTE
上级 0c743d27
......@@ -46,13 +46,15 @@
| Cascade Mask-RCNN | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ |
| Libra R-CNN | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
| RetinaNet | ✓ | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ |
| YOLOv3 | ✓ | | ✗ | ✗ | ✓ | ✗ | ✗ |
| YOLOv3 | ✓ | | ✗ | ✗ | ✓ | ✗ | ✗ |
| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ |
| BlazeFace | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Faceboxes | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
<a name="vd">[1]</a> [ResNet-vd](https://arxiv.org/pdf/1812.01187) 模型预测速度基本不变的情况下提高了精度。
**说明:** ✓ 为[模型库](docs/MODEL_ZOO_cn.md)中提供了对应配置文件和预训练模型,✗ 为未提供参考配置,但一般都支持。
更多的模型:
- EfficientDet
......
......@@ -60,13 +60,15 @@ Supported Architectures:
| Cascade Mask-RCNN | ✓ | ✗ | ✗ | ✓ | ✗ | ✗ | ✗ |
| Libra R-CNN | ✗ | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ |
| RetinaNet | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| YOLOv3 | ✓ | | ✗ | ✗ | ✓ | ✗ | ✗ |
| YOLOv3 | ✓ | | ✗ | ✗ | ✓ | ✗ | ✗ |
| SSD | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ |
| BlazeFace | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| Faceboxes | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
<a name="vd">[1]</a> [ResNet-vd](https://arxiv.org/pdf/1812.01187) models offer much improved accuracy with negligible performance cost.
**NOTE:** ✓ for config file and pretrain model provided in [Model Zoo](docs/MODEL_ZOO.md), ✗ for not provided but is supported generally.
More models:
- EfficientDet
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册