Update app.py

app.py

@@ -1,60 +1,35 @@
-import os
-os.system('pip install detectron2 -f https://dl.fbaipublicfiles.com/detectron2/wheels/cu102/torch1.9/index.html')
-os.system("git clone https://github.com/microsoft/unilm.git")
-
-import sys
-sys.path.append("unilm")
-
-import cv2
-
-from unilm.dit.object_detection.ditod import add_vit_config
-
-import torch
-
-from detectron2.config import CfgNode as CN
-from detectron2.config import get_cfg
-from detectron2.utils.visualizer import ColorMode, Visualizer
-from detectron2.data import MetadataCatalog
-from detectron2.engine import DefaultPredictor
-
 import gradio as gr
+import base64
+import io
+import requests
+import json
+from PIL import Image
 
 
-# Step 1: instantiate config
-cfg = get_cfg()
-add_vit_config(cfg)
-cfg.merge_from_file("cascade_dit_base.yml")
+def analyze_image(img):
+    #img64 = base64.b64decode(image)
+    im = Image.fromarray(image)
+    in_mem_file = io.BytesIO()
+    im.save(in_mem_file, format="png")
 
-# Step 2: add model weights URL to config
-cfg.MODEL.WEIGHTS = "https://layoutlm.blob.core.windows.net/dit/dit-fts/publaynet_dit-b_cascade.pth"
+    payload = {
+        "model":"Baseline",
+        "tasktype":"Extraction",
+        "questions":[{"Pages":[1],"Text":question}],
+        "image": base64.b64encode(in_mem_file.getvalue()).decode()
+    } 
+    url = "https://ky8mfb27dj.execute-api.us-east-1.amazonaws.com/dev/analyzedocument/submit"
 
-# Step 3: set device
-cfg.MODEL.DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
-test = ""
-# Step 4: define model
-predictor = DefaultPredictor(cfg)
+    payload = json.dumps(payload)
+    headers = {'Content-Type': 'application/json'}
 
+    response = requests.request("POST", url, headers=headers, data=payload)
 
-def analyze_image(img):
-    md = MetadataCatalog.get(cfg.DATASETS.TEST[0])
-    if cfg.DATASETS.TEST[0]=='icdar2019_test':
-        md.set(thing_classes=["table"])
-    else:
-        md.set(thing_classes=["text","title","list","table","figure"])
-    
-    output = predictor(img)["instances"]
-    v = Visualizer(img[:, :, ::-1],
-                    md,
-                    scale=1.0,
-                    instance_mode=ColorMode.SEGMENTATION)
-    result = v.draw_instance_predictions(output.to("cpu"))
-    result_image = result.get_image()[:, :, ::-1]
-    
-    return result_image
+    return response.text
     
-title = "Interactive demo: Document Layout Analysis with DiT"
-description = "Demo for Microsoft's DiT, the Document Image Transformer for state-of-the-art document understanding tasks. This particular model is fine-tuned on PubLayNet, a large dataset for document layout analysis (read more at the links below). 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/2203.02378' target='_blank'>Paper</a> | <a href='https://github.com/microsoft/unilm/tree/master/dit' target='_blank'>Github Repo</a></p> | <a href='https://huggingface.co/docs/transformers/master/en/model_doc/dit' target='_blank'>HuggingFace doc</a></p>"
+description = "Hyland Demo for Document Question & Answering , fine-tuned on DocVQA (document visual question answering). To use it, simply upload your image and type a question and click 'submit', or click one of the examples to load them. Read more at the links below."
+title = "DocVQA"
+article = "<p style='text-align: center'><a href='https://www.docvqa.org/datasets/docvqa' target='_blank'>DocVQA: Challenge | <a href='https://rrc.cvc.uab.es/?ch=17' target='_blank'>Overview - Document Visual Question Answering</a></p>"
 examples =[['publaynet_example.jpeg']]
 css = ".output-image, .input-image, .image-preview {height: 600px !important}"