Update README.md
Browse files
README.md
CHANGED
|
@@ -24,13 +24,13 @@ YOLO11 weights trained on 35k human annotated image crops and 100k generated ima
|
|
| 24 |
<span style='color:gray'>Warning: For single-molecule input (used as a classification model), appropriate padding can be added to enhance the performance.</span>
|
| 25 |
|
| 26 |
Result in private testing:
|
| 27 |
-
| Model | mAP50 | mAP50-95 |
|
| 28 |
-
| ---- | ----- | -------- |
|
| 29 |
-
| *MolMiner* | *0.8460* | *0.5524* |
|
| 30 |
-
| MolDet-n | 0.9581 | 0.8524 |
|
| 31 |
-
| MolDet-s | 0.9652 | 0.8704 |
|
| 32 |
-
| MolDet-m | 0.9686 | 0.8736 |
|
| 33 |
-
| MolDet-l | **0.9891** | **0.9028** |
|
| 34 |
|
| 35 |
usage:
|
| 36 |
```python
|
|
@@ -53,13 +53,13 @@ YOLO11 weights trained on 26k human annotated PDF pages (patents, papers, and bo
|
|
| 53 |
|
| 54 |
|
| 55 |
Result in private testing:
|
| 56 |
-
| Model | mAP50 | mAP50-95 |
|
| 57 |
-
| ---- | ----- | -------- |
|
| 58 |
-
| *MolMiner* | *0.8990* | *0.7252* |
|
| 59 |
-
| MolDet-n | 0.9871 | 0.8732 |
|
| 60 |
-
| MolDet-s | 0.9851 | 0.8824 |
|
| 61 |
-
| MolDet-m | 0.9867 | 0.8917 |
|
| 62 |
-
| MolDet-l | **0.9913** | **0.9011** |
|
| 63 |
|
| 64 |
usage:
|
| 65 |
```python
|
|
|
|
| 24 |
<span style='color:gray'>Warning: For single-molecule input (used as a classification model), appropriate padding can be added to enhance the performance.</span>
|
| 25 |
|
| 26 |
Result in private testing:
|
| 27 |
+
| Model | mAP50 | mAP50-95 | Speed (T4 TensorRT10) |
|
| 28 |
+
| ---- | ----- | -------- | ----- |
|
| 29 |
+
| *MolMiner* | *0.8460* | *0.5524* | - |
|
| 30 |
+
| **MolDet-n (Ours)** | 0.9581 | 0.8524 | 1.5 ± 0.0 ms |
|
| 31 |
+
| **MolDet-s (Ours)** | 0.9652 | 0.8704 | 2.5 ± 0.1 ms |
|
| 32 |
+
| **MolDet-m (Ours)** | 0.9686 | 0.8736 | 4.7 ± 0.1 ms |
|
| 33 |
+
| **MolDet-l (Ours)** | **0.9891** | **0.9028** | 6.2 ± 0.1 ms |
|
| 34 |
|
| 35 |
usage:
|
| 36 |
```python
|
|
|
|
| 53 |
|
| 54 |
|
| 55 |
Result in private testing:
|
| 56 |
+
| Model | mAP50 | mAP50-95 | Speed (T4 TensorRT10) |
|
| 57 |
+
| ---- | ----- | -------- | ----- |
|
| 58 |
+
| *MolMiner* | *0.8990* | *0.7252* | - |
|
| 59 |
+
| **MolDet-n (Ours)** | 0.9871 | 0.8732 | 3.1 ± 0.0 ms |
|
| 60 |
+
| **MolDet-s (Ours)** | 0.9851 | 0.8824 | 5.5 ± 0.1 ms |
|
| 61 |
+
| **MolDet-m (Ours)** | 0.9867 | 0.8917 | 9.9 ± 0.2 ms |
|
| 62 |
+
| **MolDet-l (Ours)** | **0.9913** | **0.9011** | 13.1 ± 0.3 ms |
|
| 63 |
|
| 64 |
usage:
|
| 65 |
```python
|