Update README.md
Browse filesModel description, how to use and references
README.md
CHANGED
@@ -1,3 +1,29 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: apache-2.0
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
tags:
|
3 |
+
- Pytorch
|
4 |
license: apache-2.0
|
5 |
+
datasets:
|
6 |
+
- Publaynet
|
7 |
---
|
8 |
+
|
9 |
+
|
10 |
+
# Detectron2 Cascade-RCNN with FPN and Group Normalization on ResNext32xd4-50 trained on Publaynet for Document Layout Analysis
|
11 |
+
|
12 |
+
The model and has been trained with the Tensorflow training toolkit Tensorpack and then transferred to Pytorch using a conversion script.
|
13 |
+
The Tensorflow and Pytorch models differ slightly (padding ...), however validating the both models give and difference of < 0.03 mAP.
|
14 |
+
|
15 |
+
Please check: [Xu Zhong et. all. - PubLayNet: largest dataset ever for document layout analysis](https://arxiv.org/abs/1908.07836).
|
16 |
+
|
17 |
+
This model is different from the model used the paper.
|
18 |
+
|
19 |
+
The code has been adapted so that it can be used in a **deep**doctection pipeline.
|
20 |
+
|
21 |
+
## How this model can be used
|
22 |
+
|
23 |
+
This model can be used with the **deep**doctection in a full pipeline, along with table recognition and OCR. Check the general instruction following this [Get_started](https://github.com/deepdoctection/deepdoctection/blob/master/notebooks/Get_Started.ipynb) tutorial.
|
24 |
+
|
25 |
+
|
26 |
+
## This is an inference model only
|
27 |
+
|
28 |
+
To reduce the size of the checkpoint we removed all variables that are not necessary for inference. Therefore it cannot be used for fine-tuning. To fine tune this model please use Tensorflow, as well as its training script. More information can be found in this [this model card](https://huggingface.co/deepdoctection/tp_casc_rcnn_X_32xd4_50_FPN_GN_2FC_publaynet).
|
29 |
+
|