|
|
|
--- |
|
tags: |
|
- ultralyticsplus |
|
- yolov8 |
|
- ultralytics |
|
- yolo |
|
- vision |
|
- object-detection |
|
- pytorch |
|
|
|
library_name: ultralytics |
|
library_version: 8.0.239 |
|
inference: false |
|
|
|
datasets: |
|
- chanelcolgate/yenthienviet |
|
|
|
model-index: |
|
- name: chanelcolgate/chamdiemgianhang-vsk-v2 |
|
results: |
|
- task: |
|
type: object-detection |
|
|
|
dataset: |
|
type: chanelcolgate/yenthienviet |
|
name: yenthienviet |
|
split: validation |
|
|
|
metrics: |
|
- type: precision |
|
value: 0.85481 |
|
name: mAP@0.5(box) |
|
--- |
|
|
|
<div align="center"> |
|
<img width="640" alt="chanelcolgate/chamdiemgianhang-vsk-v2" src="https://huggingface.co/chanelcolgate/chamdiemgianhang-vsk-v2/resolve/main/thumbnail.jpg"> |
|
</div> |
|
|
|
### Supported Labels |
|
|
|
``` |
|
['BOM_GEN', 'BOM_JUN', 'BOM_KID', 'BOM_SAC', 'BOM_VTG', 'BOM_YTV', 'HOP_FEJ', 'HOP_FRE', 'HOP_JUN', 'HOP_POC', 'HOP_VTG', 'HOP_YTV', 'LOC_JUN', 'LOC_KID', 'LOC_YTV', 'LOO_DAU', 'LOO_KID', 'LOO_MAM', 'LOO_YTV', 'POS_LON', 'POS_NHO', 'POS_THA', 'TUI_GEN', 'TUI_JUN', 'TUI_KID', 'TUI_SAC', 'TUI_THV', 'TUI_THX', 'TUI_VTG', 'TUI_YTV'] |
|
``` |
|
|
|
### How to use |
|
|
|
- Install [ultralyticsplus](https://github.com/fcakyon/ultralyticsplus): |
|
|
|
```bash |
|
pip install ultralyticsplus==0.1.0 ultralytics==8.0.239 |
|
``` |
|
|
|
- Load model and perform prediction: |
|
|
|
```python |
|
from ultralyticsplus import YOLO, render_result |
|
|
|
# load model |
|
model = YOLO('chanelcolgate/chamdiemgianhang-vsk-v2') |
|
|
|
# set model parameters |
|
model.overrides['conf'] = 0.25 # NMS confidence threshold |
|
model.overrides['iou'] = 0.45 # NMS IoU threshold |
|
model.overrides['agnostic_nms'] = False # NMS class-agnostic |
|
model.overrides['max_det'] = 1000 # maximum number of detections per image |
|
|
|
# set image |
|
image = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg' |
|
|
|
# perform inference |
|
results = model.predict(image) |
|
|
|
# observe results |
|
print(results[0].boxes) |
|
render = render_result(model=model, image=image, result=results[0]) |
|
render.show() |
|
``` |
|
|
|
|