Update README.md
Browse files
README.md
CHANGED
|
@@ -1,27 +1 @@
|
|
| 1 |
-
|
| 2 |
-
license: cc-by-nc-sa-4.0
|
| 3 |
-
---
|
| 4 |
-
# layoutlmv3-base-finetuned-publaynet
|
| 5 |
-
|
| 6 |
-
The model [layoutlmv3-base-finetuned-publaynet](https://huggingface.co/HYPJUDY/layoutlmv3-base-finetuned-publaynet) is fine-tuned on the PubLayNet dataset initialized from [microsoft/layoutlmv3-base](https://huggingface.co/microsoft/layoutlmv3-base).
|
| 7 |
-
This finetuned model achieves an overall mAP @ IOU [0.50:0.95] of 95.1 on the PubLayNet validation set.
|
| 8 |
-
|
| 9 |
-
[Paper](https://arxiv.org/pdf/2204.08387.pdf) | [Code](https://aka.ms/layoutlmv3) | [Microsoft Document AI](https://www.microsoft.com/en-us/research/project/document-ai/)
|
| 10 |
-
|
| 11 |
-
|
| 12 |
-
If you find LayoutLMv3 helpful, please cite the following paper:
|
| 13 |
-
```
|
| 14 |
-
@inproceedings{huang2022layoutlmv3,
|
| 15 |
-
author={Yupan Huang and Tengchao Lv and Lei Cui and Yutong Lu and Furu Wei},
|
| 16 |
-
title={LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking},
|
| 17 |
-
booktitle={Proceedings of the 30th ACM International Conference on Multimedia},
|
| 18 |
-
year={2022}
|
| 19 |
-
}
|
| 20 |
-
```
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
## License
|
| 24 |
-
|
| 25 |
-
The content of this project itself is licensed under the [Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/).
|
| 26 |
-
Portions of the source code are based on the [transformers](https://github.com/huggingface/transformers) project.
|
| 27 |
-
[Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct)
|
|
|
|
| 1 |
+
Imported from https://huggingface.co/HYPJUDY/layoutlmv3-base-finetuned-publaynet
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|