Create Parse.py

Parse.py

@@ -0,0 +1,77 @@
+import re
+
+from transformers import DonutProcessor, VisionEncoderDecoderModel
+from datasets import load_dataset
+import torch
+
+processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-cord-v2")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+# load document image
+dataset = load_dataset("hf-internal-testing/example-documents", split="test")
+image = dataset[2]["image"]
+
+# prepare decoder inputs
+task_prompt = "<s_cord-v2>"
+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))
+{'menu': {'nm': 'CINNAMON SUGAR', 'unitprice': '17,000', 'cnt': '1 x', 'price': '17,000'}, 'sub_total': {'subtotal_price': '17,000'}, 'total': {'total_price': '17,000', 'cashprice': '20,000', 'changeprice': '3,000'}}
+Step-by-step Document Visual Question Answering (DocVQA)
+Copied
+import re
+
+from transformers import DonutProcessor, VisionEncoderDecoderModel
+from datasets import load_dataset
+import torch
+
+processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
+model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+# load document image from the DocVQA dataset
+dataset = load_dataset("hf-internal-testing/example-documents", split="test")
+image = dataset[0]["image"]
+
+# prepare decoder inputs
+task_prompt = "<s_docvqa><s_question>{user_input}</s_question><s_answer>"
+question = "When is the coffee break?"
+prompt = task_prompt.replace("{user_input}", question)
+decoder_input_ids = processor.tokenizer(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))