Theo Viel
commited on
Commit
·
c4d1dfe
1
Parent(s):
8a72e26
Add viz
Browse files
README.md
CHANGED
|
@@ -18,6 +18,9 @@ tags:
|
|
| 18 |
|
| 19 |
## Model Overview
|
| 20 |
|
|
|
|
|
|
|
|
|
|
| 21 |
### Description
|
| 22 |
|
| 23 |
The **NeMo Retriever Page Elements v3** model is a specialized object detection model designed to identify and extract key elements from charts and graphs. While the underlying technology builds upon work from [Megvii Technology](https://github.com/Megvii-BaseDetection/YOLOX), we developed our own base model through complete retraining rather than using pre-trained weights. YOLOX is an anchor-free version of YOLO (You Only Look Once), this model combines a simpler architecture with enhanced performance. The model is trained to detect **tables**, **charts**, **infographics**, **titles**, **header/footers** and **texts** in documents.
|
|
|
|
| 18 |
|
| 19 |
## Model Overview
|
| 20 |
|
| 21 |
+
|
| 22 |
+
*Preview of the model output on the example image.*
|
| 23 |
+
|
| 24 |
### Description
|
| 25 |
|
| 26 |
The **NeMo Retriever Page Elements v3** model is a specialized object detection model designed to identify and extract key elements from charts and graphs. While the underlying technology builds upon work from [Megvii Technology](https://github.com/Megvii-BaseDetection/YOLOX), we developed our own base model through complete retraining rather than using pre-trained weights. YOLOX is an anchor-free version of YOLO (You Only Look Once), this model combines a simpler architecture with enhanced performance. The model is trained to detect **tables**, **charts**, **infographics**, **titles**, **header/footers** and **texts** in documents.
|
viz.png
ADDED
|
Git LFS Details
|