Update app.py

app.py

@@ -1,5 +1,3 @@
-import os
-
 import os
 os.system('pip install git+https://github.com/huggingface/transformers.git --upgrade')
 os.system('pip install pyyaml==5.1')
@@ -8,29 +6,23 @@ os.system('pip install torch==1.8.0+cu101 torchvision==0.9.0+cu101 -f https://do
 
 # install detectron2 that matches pytorch 1.8
 # See https://detectron2.readthedocs.io/tutorials/install.html for instructions
-#os.system('pip install -q detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.8/index.html')
+os.system('pip install -q detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu101/torch1.8/index.html')
 
 ## install PyTesseract
 os.system('pip install -q pytesseract')
 
-import gradio as gr
-import torch
-import PIL
 import gradio as gr
 import numpy as np
-from transformers import LayoutLMv3ForTokenClassification,LayoutLMv3Processor
+from transformers import LayoutLMv2Processor, LayoutLMv2ForTokenClassification
 from datasets import load_dataset
 from PIL import Image, ImageDraw, ImageFont
 
-
-
-processor = LayoutLMv3Processor.from_pretrained("Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD")
-model = LayoutLMv3ForTokenClassification.from_pretrained("Ammar-alhaj-ali/LayoutLMv3-Fine-Tuning-FUNSD")
+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")
 image = Image.open(dataset[0]["image_path"]).convert("RGB")
-#image = Image.open("./invoice.png")
 image.save("document.png")
 # define id2label, label2color
 labels = dataset.features['ner_tags'].feature.names
@@ -80,17 +72,12 @@ def process_image(image):
     
     return image
 
-
-title = "Interactive demo: LayoutLMv3"
-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>"
+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 into QUESTION/ANSWER/HEADER/OTHER. To use it, simply upload an image or use the example image below. Results will show up in a few seconds."
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2012.14740'>LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding</a> | <a href='https://github.com/microsoft/unilm'>Github Repo</a></p>"
 examples =[['img1.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;} }"
-# css = ".output_image, .input_image {height: 600px !important}"
-
-css = ".image-preview {height: auto !important;}"
+css = """.output_image, .input_image {height: 600px !important}"""
 
 iface = gr.Interface(fn=process_image, 
                      inputs=gr.inputs.Image(type="pil"), 
@@ -99,6 +86,5 @@ iface = gr.Interface(fn=process_image,
                      description=description,
                      article=article,
                      examples=examples,
-                     css=css,
-                     enable_queue=True)
+                     css=css)
 iface.launch(debug=True)