Image Classification
Transformers
PyTorch
TensorBoard
English
beit
Generated from Trainer
Eval Results (legacy)
Instructions to use DunnBC22/dit-base-Document_Classification-RVL_CDIP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DunnBC22/dit-base-Document_Classification-RVL_CDIP with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="DunnBC22/dit-base-Document_Classification-RVL_CDIP") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageClassification processor = AutoImageProcessor.from_pretrained("DunnBC22/dit-base-Document_Classification-RVL_CDIP") model = AutoModelForImageClassification.from_pretrained("DunnBC22/dit-base-Document_Classification-RVL_CDIP") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,7 @@ model-index:
|
|
| 24 |
value: 0.976678084687705
|
| 25 |
language:
|
| 26 |
- en
|
|
|
|
| 27 |
---
|
| 28 |
|
| 29 |
# dit-base-Document_Classification-RVL_CDIP
|
|
@@ -87,4 +88,13 @@ The following hyperparameters were used during training:
|
|
| 87 |
- Transformers 4.28.1
|
| 88 |
- Pytorch 2.0.0
|
| 89 |
- Datasets 2.11.0
|
| 90 |
-
- Tokenizers 0.13.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
value: 0.976678084687705
|
| 25 |
language:
|
| 26 |
- en
|
| 27 |
+
license: mit
|
| 28 |
---
|
| 29 |
|
| 30 |
# dit-base-Document_Classification-RVL_CDIP
|
|
|
|
| 88 |
- Transformers 4.28.1
|
| 89 |
- Pytorch 2.0.0
|
| 90 |
- Datasets 2.11.0
|
| 91 |
+
- Tokenizers 0.13.3
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
## License Notice
|
| 95 |
+
This model is a fine-tuned derivative of a pretrained model.
|
| 96 |
+
Users must comply with the original model license.
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
## Dataset Notice
|
| 100 |
+
This model was fine-tuned on third-party datasets which may have separate licenses or usage restrictions.
|