Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# ViT Model for Document Layout Classification
|
| 2 |
|
| 3 |
This model is a fine-tuned Vision Transformer (ViT) for document layout classification based on the DocLayNet dataset.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- pierreguillou/DocLayNet-base
|
| 4 |
+
metrics:
|
| 5 |
+
- accuracy
|
| 6 |
+
base_model:
|
| 7 |
+
- google/vit-base-patch16-224-in21k
|
| 8 |
+
library_name: transformers
|
| 9 |
+
tags:
|
| 10 |
+
- vision
|
| 11 |
+
- document-layout-analysis
|
| 12 |
+
- document-classification
|
| 13 |
+
- vit
|
| 14 |
+
- doclaynet
|
| 15 |
+
---
|
| 16 |
# ViT Model for Document Layout Classification
|
| 17 |
|
| 18 |
This model is a fine-tuned Vision Transformer (ViT) for document layout classification based on the DocLayNet dataset.
|