Update README.md
Browse files
README.md
CHANGED
|
@@ -1,36 +1,35 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
language:
|
| 4 |
-
|
| 5 |
tags:
|
| 6 |
-
|
| 7 |
-
|
| 8 |
library_name: burial_mounds
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
# kardosdrur/burial-mounds-yolov8m-obb
|
| 12 |
|
| 13 |
-
This repository contains a YOLO model that has been finetuned by the `burial_mounds` Python package on the `
|
|
|
|
|
|
|
| 14 |
|
| 15 |
## Usage
|
| 16 |
```python
|
| 17 |
# pip install burial_mounds
|
| 18 |
|
| 19 |
-
from burial_mounds.
|
| 20 |
|
| 21 |
-
model = load_from_hub("kardosdrur/burial-mounds-yolov8m
|
| 22 |
|
| 23 |
-
|
|
|
|
|
|
|
|
|
|
| 24 |
|
| 25 |
-
#
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
masks = result.masks # Masks object for segmentation masks outputs
|
| 29 |
-
keypoints = result.keypoints # Keypoints object for pose outputs
|
| 30 |
-
probs = result.probs # Probs object for classification outputs
|
| 31 |
-
obb = result.obb # Oriented boxes object for OBB outputs
|
| 32 |
-
result.show() # display to screen
|
| 33 |
-
result.save(filename="result.jpg") # save to disk
|
| 34 |
```
|
| 35 |
|
| 36 |
-
For a more detailed guide consult the [YOLOv8 documentation](https://docs.ultralytics.com/modes/predict/#key-features-of-predict-mode).
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- en
|
| 4 |
tags:
|
| 5 |
+
- yolo
|
| 6 |
+
- object-detection
|
| 7 |
library_name: burial_mounds
|
| 8 |
+
license: cc-by-nc-4.0
|
| 9 |
---
|
| 10 |
|
| 11 |
# kardosdrur/burial-mounds-yolov8m-obb
|
| 12 |
|
| 13 |
+
This repository contains a YOLO model that has been finetuned by the `burial_mounds` Python package on the `Mounds` dataset.
|
| 14 |
+
|
| 15 |
+
> The model is for academic use only, commercial use is prohibited due to restrictions imposed by the training datasets.
|
| 16 |
|
| 17 |
## Usage
|
| 18 |
```python
|
| 19 |
# pip install burial_mounds
|
| 20 |
|
| 21 |
+
from burial_mounds.model import MoundDetector
|
| 22 |
|
| 23 |
+
model = MoundDetector.load_from_hub("kardosdrur/burial-mounds-yolov8m")
|
| 24 |
|
| 25 |
+
# Find bounding polygons
|
| 26 |
+
bounding_polygons = model.detect_mounds("some_satellite_image.png")
|
| 27 |
+
for polygon in bounding_polygons:
|
| 28 |
+
print(polygon)
|
| 29 |
|
| 30 |
+
# Annotate satellite images
|
| 31 |
+
annotated_image = model.annotate_image("some_satellite_image.png")
|
| 32 |
+
annotated_image.show()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
```
|
| 34 |
|
| 35 |
+
For a more detailed guide consult the [YOLOv8 documentation](https://docs.ultralytics.com/modes/predict/#key-features-of-predict-mode) or [our documentation](https://github.com/x-tabdeveloping/burial-mounds-object-recognition).
|