Almost done

app.py

@@ -27,6 +27,7 @@ image = Image.open("./test0.jpeg")
 labels = dataset.features['ner_tags'].feature.names
 id2label = {v: k for v, k in enumerate(labels)}
 
+#Need to get discrete colors for each labels
 label_ints = np.random.randint(0, len(ImageColor.colormap.items()), 61)
 label_color_pil = [k for k,_ in ImageColor.colormap.items()]
 label_color = [label_color_pil[i] for i in label_ints]
@@ -78,24 +79,20 @@ def process_image(image):
     return 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 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']]
+title = "Extracting Receipts: LayoutLMv3"
+description = "Demo for Microsoft's LayoutLMv3, a Transformer for state-of-the-art document image understanding tasks. \
+This particular model is fine-tuned from [LayoutLMv3](https://huggingface.co/microsoft/layoutlmv3-base) on Consolidated Receipt Dataset ([CORD] (https://github.com/clovaai/cord), a dataset of receipts.  If you search the 🤗 Hugging Face hub you will see other related models fine-tuned for other documents. This model is trained using fine-tuning to look for entities around menu items, subtotal, and total prices.  To perform your own fine tuning, take a look at the [notebook by Niels](https://github.com/NielsRogge/Transformers-Tutorials/tree/master/LayoutLMv3). \
+To try it out, simply upload an image or use the example image below and click 'Submit'. Results will show up in a few seconds. To see the output bigger, right-click on it, select 'Open image in new tab', and use your browser's zoom feature. "
 
-#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 {height: 600px !important}, .input_image {height: 300px !important}"
+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 = ".image-preview {height: auto !important;}"
 
 iface = gr.Interface(fn=process_image, 
-                     inputs=gr.inputs.Image(type="pil", tool="editor"), 
+                     inputs=gr.inputs.Image(type="pil"), 
                      outputs=gr.outputs.Image(type="pil", label="annotated image"),
                      title=title,
                      description=description,
                      article=article,
                      examples=examples)
-                     #css=css)
 iface.launch(debug=True)