Downloads · 30 days
0
TATR-v1.1-Fin
bsmock/TATR-v1.1-Fin
TATR-v1.1-Fin is a machine learning model from bsmock. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repo contains the model weights for TATR (Table Transformer) v1.1 trained on the FinTabNet.c dataset, using the training details in the paper: "Aligning benchmark datasets for table structure recognition".
Access
Public
Updated Aug 22, 2023
Repo size
116 MB
Likes
7
Public
Repo makeup
Click a slice to open those files.
.pth116 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Aug 19, 2023
- Updated
- Aug 22, 2023
- SHA
- 07b1843f
Datasets
Model card
From the Hugging Face model README
Model Card for TATR-v1.1-Fin
This repo contains the model weights for TATR (Table Transformer) v1.1 trained on the FinTabNet.c dataset, using the training details in the paper: "Aligning benchmark datasets for table structure recognition".
These model weights are intended to be used with the Microsoft implementation of Table Transformer (TATR).
This model works best on tightly cropped table images (5 pixels or less).
Model weights that can be loaded into the Hugging Face implementation of TATR are coming soon.
FinTabNet.c will be officially released soon. Please see our GitHub repo for a script to create FinTabNet.c from the original FinTabNet dataset.
Model Details
Model Description
- Developed by: Brandon Smock and Rohith Pesala, while at Microsoft
- License: MIT
- Finetuned from model: DETR ResNet-18
Model Sources
Please see the following for more details:
- License
- mit
- Created
- Aug 19, 2023
- Updated
- Aug 22, 2023