mirrors
/
mmyolo
mirror of https://github.com/open-mmlab/mmyolo.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

add yolov8 visualization readme (#574) 

* add yolov8 visualization readme

* add readme
pull/580/head
yechenzhi 2023-02-21 11:24:43 +08:00 committed by GitHub
parent f2a576d153
commit 4e8baf8a82
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
projects/assigner_visualization/README.md
View File

@ -6,7 +6,7 @@
This project is developed for easily showing assigning results. The script allows users to analyze where and how many positive samples each gt is assigned in the image.
Now, the script supports `YOLOv5`, `YOLOv7` and `RTMDet`.
Now, the script supports `YOLOv5`, `YOLOv7`, `YOLOv8` and `RTMDet`.
## Usage
@ -26,12 +26,18 @@ YOLOv7 assigner visualization command:
python projects/assigner_visualization/assigner_visualization.py projects/assigner_visualization/configs/yolov7_tiny_syncbn_fast_8xb16-300e_coco_assignervisualization.py -c ${checkpont}
```
YOLOv8 assigner visualization command:
```shell
python projects/assigner_visualization/assigner_visualization.py projects/assigner_visualization/configs/yolov8_s_syncbn_fast_8xb16-500e_coco_assignervisualization.py -c ${checkpont}
```
RTMdet assigner visualization command:
```shell
python projects/assigner_visualization/assigner_visualization.py projects/assigner_visualization/configs/rtmdet_s_syncbn_fast_8xb32-300e_coco_assignervisualization.py -c ${checkpont}
```
${checkpont} is the checkpont file path. Dynamic label assignment is used in `YOLOv7` and `RTMDet`, model weights will affect the positive sample allocation results, so it is recommended to load the trained model weights.
${checkpont} is the checkpont file path. Dynamic label assignment is used in `YOLOv7`, `YOLOv8` and `RTMDet`, model weights will affect the positive sample allocation results, so it is recommended to load the trained model weights.
If you want to know details about label assignment, you can check the [RTMDet](https://mmyolo.readthedocs.io/zh_CN/latest/algorithm_descriptions/rtmdet_description.html#id5).