Update app.py

app.py

@@ -18,30 +18,42 @@ model.to(device)
 #print(np.array(image).shape)
 
 
-# load document image
-dataset = load_dataset("hf-internal-testing/example-documents", split="test")
-image = dataset[2]["image"]
-
-
-task_prompt = "<s_rvlcdip>"
-decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
-
-pixel_values = processor(image, return_tensors="pt").pixel_values
-
-outputs = model.generate(
-    pixel_values.to(device),
-    decoder_input_ids=decoder_input_ids.to(device),
-    max_length=model.decoder.config.max_position_embeddings,
-    pad_token_id=processor.tokenizer.pad_token_id,
-    eos_token_id=processor.tokenizer.eos_token_id,
-    use_cache=True,
-    bad_words_ids=[[processor.tokenizer.unk_token_id]],
-    return_dict_in_generate=True,
-)
-
-sequence = processor.batch_decode(outputs.sequences)[0]
-sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
-sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
-print(processor.token2json(sequence))
+st.title("Classify Document Image")
+
+file_name = st.file_uploader("Upload a candidate image")
+
+if file_name is not None:
+    col1, col2 = st.columns(2)
+
+    image = Image.open(file_name)
+    image = image.convert("RGB")
+
+    # load document image
+    #dataset = load_dataset("hf-internal-testing/example-documents", split="test")
+    #image = dataset[2]["image"]
+
+
+    task_prompt = "<s_rvlcdip>"
+    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
+
+    pixel_values = processor(image, return_tensors="pt").pixel_values
+
+    outputs = model.generate(
+        pixel_values.to(device),
+        decoder_input_ids=decoder_input_ids.to(device),
+        max_length=model.decoder.config.max_position_embeddings,
+        pad_token_id=processor.tokenizer.pad_token_id,
+        eos_token_id=processor.tokenizer.eos_token_id,
+        use_cache=True,
+        bad_words_ids=[[processor.tokenizer.unk_token_id]],
+        return_dict_in_generate=True,
+    )
+
+    sequence = processor.batch_decode(outputs.sequences)[0]
+    sequence = sequence.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
+    sequence = re.sub(r"<.*?>", "", sequence, count=1).strip()  # remove first task start token
+    print(processor.token2json(sequence))
+   
+