Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,51 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- google/efficientnet-b0
|
| 5 |
+
---
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
# EfficientNet-B0 Document Image Classifier
|
| 9 |
+
|
| 10 |
+
This is an image classification model based on **Google EfficientNet-B0**, fine-tuned to classify input images into one of the following 16 categories:
|
| 11 |
+
|
| 12 |
+
1. **bar_chart**
|
| 13 |
+
2. **bar_code**
|
| 14 |
+
3. **chemistry_markush_structure**
|
| 15 |
+
4. **chemistry_molecular_structure**
|
| 16 |
+
5. **flow_chart**
|
| 17 |
+
6. **icon**
|
| 18 |
+
7. **line_chart**
|
| 19 |
+
8. **logo**
|
| 20 |
+
9. **map**
|
| 21 |
+
10. **other**
|
| 22 |
+
11. **pie_chart**
|
| 23 |
+
12. **qr_code**
|
| 24 |
+
13. **remote_sensing**
|
| 25 |
+
14. **screenshot**
|
| 26 |
+
15. **signature**
|
| 27 |
+
16. **stamp**
|
| 28 |
+
|
| 29 |
+
## Citation
|
| 30 |
+
If you use this model in your work, please cite the following papers:
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
@article{Tan2019EfficientNetRM,
|
| 34 |
+
title={EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
|
| 35 |
+
author={Mingxing Tan and Quoc V. Le},
|
| 36 |
+
journal={ArXiv},
|
| 37 |
+
year={2019},
|
| 38 |
+
volume={abs/1905.11946}
|
| 39 |
+
}
|
| 40 |
+
|
| 41 |
+
@techreport{Docling,
|
| 42 |
+
author = {Deep Search Team},
|
| 43 |
+
month = {8},
|
| 44 |
+
title = {{Docling Technical Report}},
|
| 45 |
+
url={https://arxiv.org/abs/2408.09869},
|
| 46 |
+
eprint={2408.09869},
|
| 47 |
+
doi = "10.48550/arXiv.2408.09869",
|
| 48 |
+
version = {1.0.0},
|
| 49 |
+
year = {2024}
|
| 50 |
+
}
|
| 51 |
+
```
|