Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,10 @@ tags:
|
|
| 19 |
|
| 20 |
> **Formula-Text-Detection** is a vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for **binary image classification**. It is built using the **SiglipForImageClassification** architecture to distinguish between **mathematical formulas** and **natural text** in document or image regions.
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
```py
|
| 23 |
Classification Report:
|
| 24 |
precision recall f1-score support
|
|
@@ -100,6 +104,22 @@ iface = gr.Interface(
|
|
| 100 |
if __name__ == "__main__":
|
| 101 |
iface.launch()
|
| 102 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 103 |
|
| 104 |
---
|
| 105 |
|
|
|
|
| 19 |
|
| 20 |
> **Formula-Text-Detection** is a vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for **binary image classification**. It is built using the **SiglipForImageClassification** architecture to distinguish between **mathematical formulas** and **natural text** in document or image regions.
|
| 21 |
|
| 22 |
+
> [!Note]
|
| 23 |
+
> Note: This model works best with plain text or formulas using the same font style
|
| 24 |
+
|
| 25 |
+
|
| 26 |
```py
|
| 27 |
Classification Report:
|
| 28 |
precision recall f1-score support
|
|
|
|
| 104 |
if __name__ == "__main__":
|
| 105 |
iface.launch()
|
| 106 |
```
|
| 107 |
+
## **Demo Inference**
|
| 108 |
+
|
| 109 |
+
> [!Important]
|
| 110 |
+
> Text
|
| 111 |
+
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
|
| 115 |
+
|
| 116 |
+
|
| 117 |
+
> [!Important]
|
| 118 |
+
> Formula
|
| 119 |
+
|
| 120 |
+
|
| 121 |
+
|
| 122 |
+
|
| 123 |
|
| 124 |
---
|
| 125 |
|