metadata
language:
- es
- en
- multilingual
license: other
tags:
- image-classification
pipeline_tag: image-classification
widget:
- src: >-
https://upserve.com/media/sites/2/Bill-from-Mezcalero-in-Washington-D.C.-photo-by-Alfredo-Solis-1-e1507226752437.jpg
example_title: receipt
- src: https://templates.invoicehome.com/invoice-template-us-neat-750px.png
example_title: invoice
InvoiceReceiptClassifier_LayoutLMv3 is a fine-tuned LayoutLMv3 model that classifies a document to an invoice or receipt.
Quick start: using the raw model
from transformers import (
AutoModelForSequenceClassification,
AutoProcessor,
)
from PIL import Image
from urllib.request import urlopen
model = AutoModelForSequenceClassification.from_pretrained("fedihch/InvoiceReceiptClassifier_LayoutLMv3")
processor = AutoProcessor.from_pretrained("fedihch/InvoiceReceiptClassifier_LayoutLMv3")
input_img_url = "https://upload.wikimedia.org/wikipedia/commons/thumb/0/0b/ReceiptSwiss.jpg/1024px-ReceiptSwiss.jpg"
with urlopen(input_img_url) as testImage:
input_img = Image.open(testImage).convert("RGB")
encoded_inputs = processor(input_img, padding="max_length", return_tensors="pt")
outputs = model(**encoded_inputs)
logits = outputs.logits
predicted_class_idx = logits.argmax(-1).item()
id2label = {0: "invoice", 1: "receipt"}
print(id2label[predicted_class_idx])