MikkoLipsanen
commited on
Commit
•
55a7d3c
1
Parent(s):
94e6420
Update README.md
Browse files
README.md
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
- Ultralytics/YOLOv8
|
|
|
4 |
---
|
5 |
|
6 |
## Text column and row line intersection detection from Finnish census records from the 1930s
|
@@ -72,22 +73,22 @@ model.train(data=yaml_path, name='model_name', epochs=100, imgsz=2560, max_det=5
|
|
72 |
## Evaluation results
|
73 |
|
74 |
Evaluation results using the validation dataset are listed below:
|
75 |
-
|Class|Images|Class instances|Box precision|Box recall|Box mAP50|Box mAP50-95
|
76 |
-
|
77 |
-
|
78 |
|
79 |
More information on the performance metrics can be found [here](https://docs.ultralytics.com/guides/yolo-performance-metrics/).
|
80 |
|
81 |
## Inference
|
82 |
|
83 |
-
If the model file `
|
84 |
and the input image path is `\data\image.jpg', inference can be perfomed using the following code:
|
85 |
|
86 |
```
|
87 |
from ultralytics import YOLO
|
88 |
|
89 |
# Initialize model
|
90 |
-
model = YOLO(`\models\
|
91 |
prediction_results = model.predict(source=`\data\image.jpg', save=True)
|
92 |
```
|
93 |
More information for available inference arguments can be found [here](https://docs.ultralytics.com/modes/predict/#inference-arguments).
|
|
|
1 |
---
|
2 |
base_model:
|
3 |
- Ultralytics/YOLOv8
|
4 |
+
pipeline_tag: object-detection
|
5 |
---
|
6 |
|
7 |
## Text column and row line intersection detection from Finnish census records from the 1930s
|
|
|
73 |
## Evaluation results
|
74 |
|
75 |
Evaluation results using the validation dataset are listed below:
|
76 |
+
|Class|Images|Class instances|Box precision|Box recall|Box mAP50|Box mAP50-95
|
77 |
+
-|-|-|-|-|-|-
|
78 |
+
Intersection|25|10411|0.996|0.997|0.994|0.653|0.935|0.907|0.954|0.55
|
79 |
|
80 |
More information on the performance metrics can be found [here](https://docs.ultralytics.com/guides/yolo-performance-metrics/).
|
81 |
|
82 |
## Inference
|
83 |
|
84 |
+
If the model file `huoneistokortit_13082024.pt` is downloaded to a folder `\models\ huoneistokortit_13082024.pt`
|
85 |
and the input image path is `\data\image.jpg', inference can be perfomed using the following code:
|
86 |
|
87 |
```
|
88 |
from ultralytics import YOLO
|
89 |
|
90 |
# Initialize model
|
91 |
+
model = YOLO(`\models\ huoneistokortit_13082024.pt`)
|
92 |
prediction_results = model.predict(source=`\data\image.jpg', save=True)
|
93 |
```
|
94 |
More information for available inference arguments can be found [here](https://docs.ultralytics.com/modes/predict/#inference-arguments).
|