Image mods

app.py

@@ -23,7 +23,6 @@ model = LayoutLMv3ForTokenClassification.from_pretrained("nielsr/layoutlmv3-fine
 dataset = load_dataset("nielsr/cord-layoutlmv3", split="test")
 #image = Image.open(dataset[0]["image_path"]).convert("RGB")
 image = Image.open("./test0.jpeg")
-#image.save("document.png")
 # define id2label, label2color
 labels = dataset.features['ner_tags'].feature.names
 id2label = {v: k for v, k in enumerate(labels)}
@@ -35,8 +34,6 @@ label2color = {}
 for k,v in id2label.items():
     label2color[v[2:]]=label_color[k]
 
-#label2color = {'question':'blue', 'answer':'green', 'header':'orange', 'other':'violet'}
-
 def unnormalize_box(bbox, width, height):
      return [
          width * (bbox[0] / 1000),
@@ -75,8 +72,6 @@ def process_image(image):
     font = ImageFont.load_default()
     for prediction, box in zip(true_predictions, true_boxes):
         predicted_label = iob_to_label(prediction) #.lower()
-        #print (predicted_label)
-        #print (label2color[predicted_label])
         draw.rectangle(box, outline=label2color[predicted_label])
         draw.text((box[0]+10, box[1]-10), text=predicted_label, fill=label2color[predicted_label], font=font)
     
@@ -84,13 +79,14 @@ def process_image(image):
 
 
 title = "Interactive demo: LayoutLMv3"
-description = "Demo for Microsoft's LayoutLMv3, a Transformer for state-of-the-art document image understanding tasks. This particular model is fine-tuned on CORD, a dataset of ***. It annotates the words appearing in the image as ***. 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'."
+description = "Demo for Microsoft's LayoutLMv3, a Transformer for state-of-the-art document image understanding tasks. This particular model is fine-tuned on CORD, a dataset of receipts. It annotates the words appearing in the image as ***. 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/2204.08387' target='_blank'>LayoutLMv3: Multi-modal Pre-training for Visually-Rich Document Understanding</a> | <a href='https://github.com/microsoft/unilm' target='_blank'>Github Repo</a></p>"
 examples =[['test0.jpeg'],['./test1.jpeg'],['test2.jpeg']]
 
-css = ".output-image, .input-image {height: 40rem !important; width: 100% !important;}"
+css = ".output-image, .input-image"
+#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 = ".output_image, .input_image {height: 600px !important}"
 
 css = ".image-preview {height: auto !important;}"