# Load model directly
from transformers import AutoProcessor, AutoModelForTokenClassification
processor = AutoProcessor.from_pretrained("Sennodipoi/LayoutLMv3-FUNSD-ft")
model = AutoModelForTokenClassification.from_pretrained("Sennodipoi/LayoutLMv3-FUNSD-ft")Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
LayoutLMv3 fine-tuned on the FUNSD dataset. Code and results are available at the official GitHub repository of my Master Degree thesis .
Results obtained using seqeval in strict mode:
| Precision | Recall | F1-score | Variance (F1) | |
|---|---|---|---|---|
| Answer | 0.90 | 0.91 | 0.90 | 3e-5 |
| Header | 0.61 | 0.66 | 0.63 | 4e-4 |
| Question | 0.88 | 0.87 | 0.88 | 1e-4 |
| Micro avg | 0.87 | 0.88 | 0.87 | 3e-5 |
| Macro avg | 0.79 | 0.82 | 0.80 | 3e-5 |
| Weighted avg | 0.87 | 0.88 | 0.87 | 3e-5 |
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="Sennodipoi/LayoutLMv3-FUNSD-ft")