fix error

README.md

@@ -6,7 +6,7 @@ colorTo: green
 sdk: gradio
 app_file: app.py
 pinned: false
-sdk_version: 5.7.1
+sdk_version: 6.1.0
 ---
 
 # Configuration

app.py

@@ -3,23 +3,19 @@ import os
 # build detectron2 from source
 # we can't build detectron2 in requirements.txt because it needs PyTorch installed first,
 # but requirements.txt will try to build wheels before installing any packages.
-os.system("pip install git+https://github.com/facebookresearch/detectron2.git")
+os.system("pip install git+https://github.com/facebookresearch/detectron2.git --no-build-isolation")
 
 import gradio as gr
 import numpy as np
 from datasets import load_dataset
-from PIL import Image, ImageDraw, ImageFont
+from PIL import ImageDraw, ImageFont
 from transformers import LayoutLMv2ForTokenClassification, LayoutLMv2Processor
 
 processor = LayoutLMv2Processor.from_pretrained("microsoft/layoutlmv2-base-uncased")
 model = LayoutLMv2ForTokenClassification.from_pretrained("nielsr/layoutlmv2-finetuned-funsd")
 
-# load image example
-dataset = load_dataset("nielsr/funsd", split="test", trust_remote_code=True)
-image = Image.open(dataset[0]["image"]).convert("RGB")
-image = Image.open("./invoice.png")
-image.save("document.png")
 # define id2label, label2color
+dataset = load_dataset("nielsr/funsd", split="test")
 labels = dataset.features["ner_tags"].feature.names
 id2label = {v: k for v, k in enumerate(labels)}
 label2color = {"question": "blue", "answer": "green", "header": "orange", "other": "violet"}
@@ -74,7 +70,7 @@ def process_image(image):
 title = "Interactive demo: LayoutLMv2"
 description = "Demo for Microsoft's LayoutLMv2, a Transformer for state-of-the-art document image understanding tasks. This particular model is fine-tuned on FUNSD, a dataset of manually annotated forms. It annotates the words appearing in the image as QUESTION/ANSWER/HEADER/OTHER. To use it, simply upload an image or use the example image below and click 'Submit'. Results will show up in a few seconds. If you want to make the output bigger, right-click on it and select 'Open image in new tab'."
 article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2012.14740' target='_blank'>LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding</a> | <a href='https://github.com/microsoft/unilm' target='_blank'>Github Repo</a></p>"
-examples = [["document.png"]]
+examples = [["invoice.png"]]
 
 css = ".output-image, .input-image {height: 40rem !important; width: 100% !important;}"
 # css = "@media screen and (max-width: 600px) { .output_image, .input_image {height:20rem !important; width: 100% !important;} }"

requirements.txt

@@ -2,7 +2,8 @@
 --extra-index-url https://pypi.org/simple
 Pillow
 numpy
-torch
-torchvision
-transformers
+torch==2.9.1
+torchvision==0.24.1
+transformers==4.57.3
+datasets==4.4.1
 pytesseract