Object Detection
ultralytics
English
German
yolo
yolov8
invoice
document-layout
document-understanding
ocr-prep
invoice-extraction
Eval Results (legacy)
Instructions to use AvoCahDoe/invoice-layout-yolov8s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ultralytics
How to use AvoCahDoe/invoice-layout-yolov8s with ultralytics:
from ultralytics import YOLOvv8 model = YOLOvv8.from_pretrained("AvoCahDoe/invoice-layout-yolov8s") source = 'http://images.cocodataset.org/val2017/000000039769.jpg' model.predict(source=source, save=True) - Notebooks
- Google Colab
- Kaggle
Upload metrics/comparison.json with huggingface_hub
Browse files- metrics/comparison.json +113 -0
metrics/comparison.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"models": [
|
| 3 |
+
{
|
| 4 |
+
"model": "yolov8n",
|
| 5 |
+
"run_dir": "E:\\invoice-extractor\\training_model\\runs\\comparison\\yolov8n",
|
| 6 |
+
"best_epoch": 53,
|
| 7 |
+
"train_box_loss": 1.19897,
|
| 8 |
+
"train_cls_loss": 1.03001,
|
| 9 |
+
"val_box_loss": 1.29424,
|
| 10 |
+
"val_cls_loss": 1.00109,
|
| 11 |
+
"precision": 0.93255,
|
| 12 |
+
"recall": 0.76417,
|
| 13 |
+
"map50": 0.88236,
|
| 14 |
+
"map50_95": 0.5973,
|
| 15 |
+
"test_precision": 0.9502026366186389,
|
| 16 |
+
"test_recall": 0.9592350761984346,
|
| 17 |
+
"test_map50": 0.96,
|
| 18 |
+
"test_map50_95": 0.7167417072510822,
|
| 19 |
+
"test_speed_ms": 0.0
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"model": "yolov8s",
|
| 23 |
+
"run_dir": "E:\\invoice-extractor\\training_model\\runs\\comparison\\yolov8s",
|
| 24 |
+
"best_epoch": 84,
|
| 25 |
+
"train_box_loss": 1.12892,
|
| 26 |
+
"train_cls_loss": 0.98365,
|
| 27 |
+
"val_box_loss": 1.19847,
|
| 28 |
+
"val_cls_loss": 0.92536,
|
| 29 |
+
"precision": 0.89289,
|
| 30 |
+
"recall": 0.79291,
|
| 31 |
+
"map50": 0.85802,
|
| 32 |
+
"map50_95": 0.58125,
|
| 33 |
+
"test_precision": 0.9418900776026258,
|
| 34 |
+
"test_recall": 0.8677204132580655,
|
| 35 |
+
"test_map50": 0.900625,
|
| 36 |
+
"test_map50_95": 0.673915781700938,
|
| 37 |
+
"test_speed_ms": 0.0
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"model": "yolov8m",
|
| 41 |
+
"run_dir": "E:\\invoice-extractor\\training_model\\runs\\comparison\\yolov8m",
|
| 42 |
+
"best_epoch": 96,
|
| 43 |
+
"train_box_loss": 1.35495,
|
| 44 |
+
"train_cls_loss": 1.13978,
|
| 45 |
+
"val_box_loss": 1.50381,
|
| 46 |
+
"val_cls_loss": 1.16088,
|
| 47 |
+
"precision": 0.86048,
|
| 48 |
+
"recall": 0.79786,
|
| 49 |
+
"map50": 0.86459,
|
| 50 |
+
"map50_95": 0.54281,
|
| 51 |
+
"test_precision": 0.9077380952380952,
|
| 52 |
+
"test_recall": 0.8579545454545455,
|
| 53 |
+
"test_map50": 0.8388392857142857,
|
| 54 |
+
"test_map50_95": 0.5289323468472317,
|
| 55 |
+
"test_speed_ms": 0.0
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"model": "yolo11m",
|
| 59 |
+
"run_dir": "E:\\invoice-extractor\\training_model\\runs\\comparison\\yolo11m",
|
| 60 |
+
"best_epoch": 87,
|
| 61 |
+
"train_box_loss": 1.5606,
|
| 62 |
+
"train_cls_loss": 1.49963,
|
| 63 |
+
"val_box_loss": 1.9019,
|
| 64 |
+
"val_cls_loss": 1.35903,
|
| 65 |
+
"precision": 0.85334,
|
| 66 |
+
"recall": 0.81873,
|
| 67 |
+
"map50": 0.88242,
|
| 68 |
+
"map50_95": 0.41246,
|
| 69 |
+
"test_precision": 0.9032503333433675,
|
| 70 |
+
"test_recall": 0.8465909090909092,
|
| 71 |
+
"test_map50": 0.8418105158730158,
|
| 72 |
+
"test_map50_95": 0.4925741071428572,
|
| 73 |
+
"test_speed_ms": 0.0
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"model": "yolov8x",
|
| 77 |
+
"run_dir": "E:\\invoice-extractor\\training_model\\runs\\comparison\\yolov8x",
|
| 78 |
+
"best_epoch": 98,
|
| 79 |
+
"train_box_loss": 1.19512,
|
| 80 |
+
"train_cls_loss": 1.00977,
|
| 81 |
+
"val_box_loss": 1.33924,
|
| 82 |
+
"val_cls_loss": 1.07422,
|
| 83 |
+
"precision": 0.90676,
|
| 84 |
+
"recall": 0.7602,
|
| 85 |
+
"map50": 0.87977,
|
| 86 |
+
"map50_95": 0.59026,
|
| 87 |
+
"test_precision": 0.9144471501244504,
|
| 88 |
+
"test_recall": 0.8734808033471103,
|
| 89 |
+
"test_map50": 0.8756583298524088,
|
| 90 |
+
"test_map50_95": 0.6224458809221967,
|
| 91 |
+
"test_speed_ms": 0.0
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"model": "yolo11x",
|
| 95 |
+
"run_dir": "E:\\invoice-extractor\\training_model\\runs\\comparison\\yolo11x",
|
| 96 |
+
"best_epoch": 85,
|
| 97 |
+
"train_box_loss": 1.43351,
|
| 98 |
+
"train_cls_loss": 1.25472,
|
| 99 |
+
"val_box_loss": 1.29899,
|
| 100 |
+
"val_cls_loss": 0.9381,
|
| 101 |
+
"precision": 0.88984,
|
| 102 |
+
"recall": 0.79349,
|
| 103 |
+
"map50": 0.89438,
|
| 104 |
+
"map50_95": 0.61416,
|
| 105 |
+
"test_precision": 0.9484481709774795,
|
| 106 |
+
"test_recall": 0.8530167875685298,
|
| 107 |
+
"test_map50": 0.87375,
|
| 108 |
+
"test_map50_95": 0.6127151988636363,
|
| 109 |
+
"test_speed_ms": 0.0
|
| 110 |
+
}
|
| 111 |
+
],
|
| 112 |
+
"dataset": "E:\\invoice-extractor\\training_model\\data\\yolo_annotated\\dataset.yaml"
|
| 113 |
+
}
|