Instructions to use pascalrai/Deformable-DETR-Document-Layout-Analysis with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use pascalrai/Deformable-DETR-Document-Layout-Analysis with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("object-detection", model="pascalrai/Deformable-DETR-Document-Layout-Analysis")# Load model directly from transformers import AutoImageProcessor, AutoModelForObjectDetection processor = AutoImageProcessor.from_pretrained("pascalrai/Deformable-DETR-Document-Layout-Analysis") model = AutoModelForObjectDetection.from_pretrained("pascalrai/Deformable-DETR-Document-Layout-Analysis") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -104,6 +104,8 @@ Evaluation of the Trained model on Test Dataset of DocLayNet (On 3 epoch):
|
|
| 104 |
|
| 105 |
### Training hyperparameters
|
| 106 |
|
|
|
|
|
|
|
| 107 |
The following hyperparameters were used during training:
|
| 108 |
- learning_rate: 5e-05
|
| 109 |
- eff_train_batch_size: 12
|
|
|
|
| 104 |
|
| 105 |
### Training hyperparameters
|
| 106 |
|
| 107 |
+
The model was trained on A10G 24GB GPU for 21 hours.
|
| 108 |
+
|
| 109 |
The following hyperparameters were used during training:
|
| 110 |
- learning_rate: 5e-05
|
| 111 |
- eff_train_batch_size: 12
|