Init commit

app.py

@@ -0,0 +1,44 @@
+from PIL import Image
+from transformers import DonutProcessor, VisionEncoderDecoderModel
+import torch
+import re
+import gradio as gr
+
+processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")
+model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-rvlcdip")
+
+def ClassificateDocs(pathimage):
+  image = Image.open(pathimage)
+  pixel_values = processor(image, return_tensors="pt").pixel_values
+  task_prompt = "<s_rvlcdip>"
+  decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
+  device = "cuda" if torch.cuda.is_available() else "cpu"
+  model.to(device)
+  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
+  return processor.token2json(sequence)
+ClassificateDocs("/content/Factura3.jpeg")
+demo = gr.Blocks()
+
+gradio_app = gr.Interface(
+    fn=ClassificateDocs,
+    inputs=[
+        gr.Image(type='filepath')
+    ],
+    outputs="text",
+)
+
+if __name__ == "__main__":
+    gradio_app.launch()

requirements.txt

@@ -0,0 +1,2 @@
+git+https://github.com/huggingface/transformers
+torch