Create app.py

app.py

@@ -0,0 +1,47 @@
+import matplotlib.pyplot as plt
+import matplotlib.patches as patches
+from matplotlib.patches import Patch
+import io
+from PIL import Image, ImageDraw58655
+import numpy as np
+import csv
+import pandas as pd
+
+from torchvision import transforms
+
+from transformers import AutoModelForObjectDetection
+import torch
+
+import easyocr
+
+import gradio as gr
+
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+def process_pdf():
+    print('process_pdf')
+    # cropped_table = detect_and_crop_table(image)
+    # image, cells = recognize_table(cropped_table)
+
+    # cell_coordinates = get_cell_coordinates_by_row(cells)
+    # df, data = apply_ocr(cell_coordinates, image)
+
+    # return image, df, data
+    return [], [], []
+
+title = "Sheriff's Demo: Table Detection & Recognition with Table Transformer (TATR)."
+description = """A demo by M Sheriff for table extraction with the Table Transformer.
+First, table detection is performed on the input image using https://huggingface.co/microsoft/table-transformer-detection,
+after which the detected table is extracted and https://huggingface.co/microsoft/table-transformer-structure-recognition-v1.1-all recognizes the
+    individual rows, columns and cells. OCR is then performed per cell, row by row."""
+examples = [['image.png'], ['mistral_paper.png']]
+
+app = gr.Interface(fn=process_pdf, 
+                     inputs=gr.Image(type="pil"), 
+                     outputs=[gr.Image(type="pil", label="Detected table"), gr.Dataframe(label="Table as CSV"), gr.JSON(label="Data as JSON")],
+                     title=title,
+                     description=description,
+                     examples=examples)
+app.queue()
+app.launch(debug=True)