Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Document Image Transformer (base-sized model)
|
| 2 |
|
| 3 |
Document Image Transformer (DiT) model pre-trained on IIT-CDIP (Lewis et al., 2006), a dataset that includes 42 million document images and fine-tuned on [RVL-CDIP](https://www.cs.cmu.edu/~aharley/rvl-cdip/), a dataset consisting of 400,000 grayscale images in 16 classes, with 25,000 images per class. It was introduced in the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://arxiv.org/abs/2203.02378) by Li et al. and first released in [this repository](https://github.com/microsoft/unilm/tree/master/dit). Note that DiT is identical to the architecture of [BEiT](https://huggingface.co/docs/transformers/model_doc/beit).
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- vision
|
| 4 |
+
- image-classification
|
| 5 |
+
widget:
|
| 6 |
+
- src: coca_cola_advertisement.png
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
# Document Image Transformer (base-sized model)
|
| 10 |
|
| 11 |
Document Image Transformer (DiT) model pre-trained on IIT-CDIP (Lewis et al., 2006), a dataset that includes 42 million document images and fine-tuned on [RVL-CDIP](https://www.cs.cmu.edu/~aharley/rvl-cdip/), a dataset consisting of 400,000 grayscale images in 16 classes, with 25,000 images per class. It was introduced in the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://arxiv.org/abs/2203.02378) by Li et al. and first released in [this repository](https://github.com/microsoft/unilm/tree/master/dit). Note that DiT is identical to the architecture of [BEiT](https://huggingface.co/docs/transformers/model_doc/beit).
|