Update app.py

app.py

@@ -116,17 +116,6 @@ def unnormalize_box(bbox, width, height):
          height * (bbox[3] / 1000),
      ]
 
-#def prepare_examples(examples):
-#  images = examples[image_column_name]
-#  words = examples[text_column_name]
-#  boxes = examples[boxes_column_name]
-#  word_labels = examples[label_column_name]
-
-#  encoding = processor(images, words, boxes=boxes, word_labels=word_labels,
- #                      truncation=True, padding="max_length")
-
- # return encoding
-
 # we need to define custom features for `set_format` (used later on) to work properly
 features = Features({
     'pixel_values': Array3D(dtype="float32", shape=(3, 224, 224)),
@@ -173,58 +162,7 @@ def process_image(image):
     
     return image
 
-#def process_image(image):
-
-    print(type(image))
-    width, height = image.size
-
-    image = example["image"]
-    words = example["tokens"]
-    boxes = example["bboxes"]
-    word_labels = example["ner_tags"]
-
-    for k,v in encoding.items():
-        print(k,v.shape)
-
-    # encode
-
-    encoding = processor(image, truncation=True,boxes=boxes, word_labels=word_labels,return_offsets_mapping=True, return_tensors="pt")
-    offset_mapping = encoding.pop('offset_mapping')
-
-    
-
-    # forward pass
-    with torch.no_grad():
-        outputs = model(**encoding)
-
-    # get predictions
-
-    # We take the highest score for each token, using argmax. 
-    # This serves as the predicted label for each token.
-    logits = outputs.logits
-    #logits.shape
-    predictions = logits.argmax(-1).squeeze().tolist()
 
-    labels = encoding.labels.squeeze().tolist()
-
-    token_boxes = encoding.bbox.squeeze().tolist()
-    width, height = image.size
-
-        
-    # only keep non-subword predictions
-    is_subword = np.array(offset_mapping.squeeze().tolist())[:,0] != 0
-    true_predictions = [id2label[pred] for idx, pred in enumerate(predictions) if not is_subword[idx]]
-    true_boxes = [unnormalize_box(box, width, height) for idx, box in enumerate(token_boxes) if not is_subword[idx]]
-
-    # draw predictions over the image
-    draw = ImageDraw.Draw(image)
-    font = ImageFont.load_default()
-    for prediction, box in zip(true_predictions, true_boxes):
-        predicted_label = id2label(prediction)
-        draw.rectangle(box, outline=label2color[predicted_label])
-        draw.text((box[0]+10, box[1]-10), text=predicted_label, fill=label2color[predicted_label], font=font)
-    
-    return image
 
 title = "DocumentAI - Extraction using LayoutLMv3 model"
 description = "Extraction of Form or Invoice Extraction - We use Microsoft's LayoutLMv3 trained on Invoice Dataset to predict the Biller Name, Biller Address, Biller post_code, Due_date, GST, Invoice_date, Invoice_number, Subtotal and Total. To use it, simply upload an image or use the example image below. Results will show up in a few seconds."