Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ tags:
|
|
| 12 |
|
| 13 |
# Molecule Detection YOLO in MolParser2.0
|
| 14 |
|
| 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
|
|
@@ -21,8 +21,6 @@ YOLO11-n weights trained on more than 100k human annotated image crops & synthes
|
|
| 21 |
|
| 22 |

|
| 23 |
|
| 24 |
-

|
| 25 |
-
|
| 26 |
features:
|
| 27 |
* 640x640 input resolution
|
| 28 |
* support handwritten molecules detection
|
|
@@ -45,9 +43,6 @@ YOLO11-n weights trained on more than 60k human annotated PDF pages (patents, pa
|
|
| 45 |
|
| 46 |

|
| 47 |
|
| 48 |
-

|
| 49 |
-

|
| 50 |
-
|
| 51 |
features:
|
| 52 |
* 960x960 input resolution
|
| 53 |
* prefer **single page PDF image** input
|
|
@@ -74,6 +69,10 @@ For further usage instructions, please refer to the [official Ultralytics docume
|
|
| 74 |
|
| 75 |
Please refer to [MolDet-Bench](https://huggingface.co/datasets/UniParser/MolDet-Bench)
|
| 76 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 77 |
|
| 78 |
## 📖 Citation
|
| 79 |
|
|
|
|
| 12 |
|
| 13 |
# Molecule Detection YOLO in MolParser2.0
|
| 14 |
|
| 15 |
+
Compared to [MolDet](https://huggingface.co/UniParser/MolDet), our new **MolDetv2** model 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
|
|
|
|
| 21 |
|
| 22 |

|
| 23 |
|
|
|
|
|
|
|
| 24 |
features:
|
| 25 |
* 640x640 input resolution
|
| 26 |
* support handwritten molecules detection
|
|
|
|
| 43 |
|
| 44 |

|
| 45 |
|
|
|
|
|
|
|
|
|
|
| 46 |
features:
|
| 47 |
* 960x960 input resolution
|
| 48 |
* prefer **single page PDF image** input
|
|
|
|
| 69 |
|
| 70 |
Please refer to [MolDet-Bench](https://huggingface.co/datasets/UniParser/MolDet-Bench)
|
| 71 |
|
| 72 |
+

|
| 73 |
+

|
| 74 |
+

|
| 75 |
+
|
| 76 |
|
| 77 |
## 📖 Citation
|
| 78 |
|