Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,7 @@ From paper: "*MolParser: End-to-end Visual Recognition of Molecule Structures in
|
|
| 8 |
|
| 9 |
We provide several [ultralytics YOLO11]((https://github.com/ultralytics/ultralytics)) weights for molecule detection with different size & input resolution.
|
| 10 |
|
|
|
|
| 11 |
## General molecule structure detection models
|
| 12 |
|
| 13 |
`moldet_yolo11[size]_640_general.pt`
|
|
@@ -43,6 +44,7 @@ YOLO11 weights trained on 26k human annotated PDF pages (patents, papers, and bo
|
|
| 43 |
|
| 44 |
* 960x960 input resolution
|
| 45 |
* prefer **single page PDF image** input
|
|
|
|
| 46 |
|
| 47 |
<span style='color:gray'>Warning: It is recommended to use MuPDF to render PDF pages at more than 144dpi.</span>
|
| 48 |
|
|
@@ -60,4 +62,6 @@ usage:
|
|
| 60 |
from ultralytics import YOLO
|
| 61 |
model = YOLO("moldet_yolo11l_960_doc.pt")
|
| 62 |
model.predict("path/to/pdf_page_image.png", save=True, imgsz=960, conf=0.5)
|
| 63 |
-
```
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
We provide several [ultralytics YOLO11]((https://github.com/ultralytics/ultralytics)) weights for molecule detection with different size & input resolution.
|
| 10 |
|
| 11 |
+
|
| 12 |
## General molecule structure detection models
|
| 13 |
|
| 14 |
`moldet_yolo11[size]_640_general.pt`
|
|
|
|
| 44 |
|
| 45 |
* 960x960 input resolution
|
| 46 |
* prefer **single page PDF image** input
|
| 47 |
+
* better in small molecule detection
|
| 48 |
|
| 49 |
<span style='color:gray'>Warning: It is recommended to use MuPDF to render PDF pages at more than 144dpi.</span>
|
| 50 |
|
|
|
|
| 62 |
from ultralytics import YOLO
|
| 63 |
model = YOLO("moldet_yolo11l_960_doc.pt")
|
| 64 |
model.predict("path/to/pdf_page_image.png", save=True, imgsz=960, conf=0.5)
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
|