Update app.py

app.py

@@ -26,14 +26,9 @@ model = AutoModelForTokenClassification.from_pretrained("SickBoy/layoutlm_docume
 
 # load image example
 dataset = load_dataset("SickBoy/layout_documents", split="train")
-example = dataset[0]
-image1 = example["image"]
-words = example["tokens"]
-boxes = example["bboxes"]
-labels = example["ner_tags"]
-#Image.open(dataset[2]["image_path"]).convert("RGB").save("example1.png")
-#Image.open(dataset[1]["image_path"]).convert("RGB").save("example2.png")
-#Image.open(dataset[0]["image_path"]).convert("RGB").save("example3.png")
+Image.open(dataset[2]["image_path"]).convert("RGB").save("example1.png")
+Image.open(dataset[1]["image_path"]).convert("RGB").save("example2.png")
+Image.open(dataset[0]["image_path"]).convert("RGB").save("example3.png")
 # define id2label, label2color
 #labels = dataset.features['ner_tags'].feature.names
 labels = ['O', 'HEADER', 'SUBHEADER', 'TEXTO', 'NUMERAL', 'RESUMEN']
@@ -81,9 +76,9 @@ def process_image(image):
     width, height = image.size
 
     # encode
-    #encoding = processor(image, truncation=True, return_offsets_mapping=True, return_tensors="pt")
-    encoding = processor(image1, words, boxes=boxes, word_labels=word_labels, return_tensors="pt")
-    #offset_mapping = encoding.pop('offset_mapping')
+    #encoding = processor(image1, words, boxes=boxes, word_labels=word_labels, return_tensors="pt")
+    encoding = processor(image, truncation=True, return_offsets_mapping=True, return_tensors="pt")
+    offset_mapping = encoding.pop('offset_mapping')
 
     # forward pass
     outputs = model(**encoding)
@@ -113,7 +108,7 @@ description = "Invoice Information Extraction - We use Microsoft's LayoutLMv3 tr
 
 article="<b>References</b><br>[1] Y. Xu et al., “LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking.” 2022. <a href='https://arxiv.org/abs/2204.08387'>Paper Link</a><br>[2]  <a href='https://github.com/NielsRogge/Transformers-Tutorials/tree/master/LayoutLMv3'>LayoutLMv3 training and inference</a>" 
 
-#examples =[['example1.png'],['example2.png'],['example3.png']]
+examples =[['example1.png'],['example2.png'],['example3.png']]
 
 css = """.output_image, .input_image {height: 600px !important}"""
 
@@ -123,7 +118,7 @@ iface = gr.Interface(fn=process_image,
                      title=title,
                      description=description,
                      article=article,
-                     #examples=examples,
+                     examples=examples,
                      css=css,
                      analytics_enabled = True, enable_queue=True)