Upload app.py
Browse files
app.py
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from transformers import LayoutLMv3Processor, LayoutLMv3ForTokenClassification
|
3 |
+
from PIL import Image
|
4 |
+
|
5 |
+
# Load model and processor
|
6 |
+
processor = LayoutLMv3Processor.from_pretrained("quadranttechnologies/Table_OCR")
|
7 |
+
model = LayoutLMv3ForTokenClassification.from_pretrained("quadranttechnologies/Table_OCR")
|
8 |
+
|
9 |
+
def predict(image):
|
10 |
+
inputs = processor(images=image, return_tensors="pt")
|
11 |
+
outputs = model(**inputs)
|
12 |
+
predictions = outputs.logits.argmax(-1).squeeze().tolist()
|
13 |
+
return {"results": predictions}
|
14 |
+
|
15 |
+
# Gradio interface
|
16 |
+
iface = gr.Interface(
|
17 |
+
fn=predict,
|
18 |
+
inputs=gr.Image(type="pil"),
|
19 |
+
outputs="json",
|
20 |
+
title="Table OCR",
|
21 |
+
description="Upload a receipt or document image to extract structured information.",
|
22 |
+
)
|
23 |
+
|
24 |
+
iface.launch()
|