Update README.md
Browse files
README.md
CHANGED
|
@@ -15,12 +15,15 @@ tags:
|
|
| 15 |
Compared to [MolDet](https://huggingface.co/UniParser/MolDet), **MolDetv2** leverages more manually annotated training data, with further optimizations specifically for reducing molecular false detections and improving bounding box regression, achieving stronger performance with a smaller model.
|
| 16 |
|
| 17 |
|
| 18 |
-
## [MolDet-General]
|
| 19 |
|
| 20 |
YOLO11-n weights trained on more than 100k human annotated image crops & synthesis molecule images.
|
| 21 |
|
| 22 |

|
| 23 |
|
|
|
|
|
|
|
|
|
|
| 24 |
* 640x640 input resolution
|
| 25 |
* support handwritten molecules detection
|
| 26 |
* **multiscale input** (inputs can be single/multiple molecular cutouts, reaction or table cutouts, or single-page PDF images)
|
|
@@ -36,12 +39,16 @@ For further usage instructions, please refer to the [official Ultralytics docume
|
|
| 36 |
|
| 37 |
|
| 38 |
|
| 39 |
-
## [MolDet-Doc]
|
| 40 |
|
| 41 |
YOLO11-n weights trained on more than 60k human annotated PDF pages (patents, papers, and books) and 10k synthesis PDF pages with molecule images.
|
| 42 |
|
| 43 |

|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
* 960x960 input resolution
|
| 46 |
* prefer **single page PDF image** input
|
| 47 |
* better in small molecule detection
|
|
@@ -67,10 +74,6 @@ For further usage instructions, please refer to the [official Ultralytics docume
|
|
| 67 |
|
| 68 |
Please refer to [MolDet-Bench](https://huggingface.co/datasets/UniParser/MolDet-Bench)
|
| 69 |
|
| 70 |
-

|
| 71 |
-

|
| 72 |
-

|
| 73 |
-
|
| 74 |
|
| 75 |
## 📖 Citation
|
| 76 |
|
|
|
|
| 15 |
Compared to [MolDet](https://huggingface.co/UniParser/MolDet), **MolDetv2** leverages more manually annotated training data, with further optimizations specifically for reducing molecular false detections and improving bounding box regression, achieving stronger performance with a smaller model.
|
| 16 |
|
| 17 |
|
| 18 |
+
## [MolDet-General] universal molecule structure detection
|
| 19 |
|
| 20 |
YOLO11-n weights trained on more than 100k human annotated image crops & synthesis molecule images.
|
| 21 |
|
| 22 |

|
| 23 |
|
| 24 |
+

|
| 25 |
+
|
| 26 |
+
features:
|
| 27 |
* 640x640 input resolution
|
| 28 |
* support handwritten molecules detection
|
| 29 |
* **multiscale input** (inputs can be single/multiple molecular cutouts, reaction or table cutouts, or single-page PDF images)
|
|
|
|
| 39 |
|
| 40 |
|
| 41 |
|
| 42 |
+
## [MolDet-Doc] document molecule structure detection
|
| 43 |
|
| 44 |
YOLO11-n weights trained on more than 60k human annotated PDF pages (patents, papers, and books) and 10k synthesis PDF pages with molecule images.
|
| 45 |
|
| 46 |

|
| 47 |
|
| 48 |
+

|
| 49 |
+

|
| 50 |
+
|
| 51 |
+
features:
|
| 52 |
* 960x960 input resolution
|
| 53 |
* prefer **single page PDF image** input
|
| 54 |
* better in small molecule detection
|
|
|
|
| 74 |
|
| 75 |
Please refer to [MolDet-Bench](https://huggingface.co/datasets/UniParser/MolDet-Bench)
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
## 📖 Citation
|
| 79 |
|