Theivaprakasham/layoutlmv3-finetuned-invoice

LayoutLM-v3 model fine-tuned on invoice dataset

This model is a fine-tuned version of microsoft/layoutlmv3-base on the invoice dataset.

We use Microsoft’s LayoutLMv3 trained on Invoice Dataset to predict the Biller Name, Biller Address, Biller postcode, Duedate, GST, Invoicedate, Invoicenumber, Subtotal and Total. To use it, simply upload an image or use the example image below. Results will show up in a few seconds.

It achieves the following results on the evaluation set:

• —Loss: 0.0012
• —Precision: 1.0
• —Recall: 1.0
• —F1: 1.0
• —Accuracy: 1.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

All the training codes are available from the below GitHub link.

https://github.com/Theivaprakasham/layoutlmv3

The model can be evaluated at the HuggingFace Spaces link:

https://huggingface.co/spaces/Theivaprakasham/layoutlmv3_invoice

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 1e-05
• —trainbatchsize: 2
• —evalbatchsize: 2
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —training_steps: 2000

Training results

Framework versions

• —Transformers 4.20.0.dev0
• —Pytorch 1.11.0+cu113
• —Datasets 2.2.2
• —Tokenizers 0.12.1