Primer push

app.py

@@ -0,0 +1,59 @@
+import numpy as np
+import gradio as gr
+import re
+import json
+import os
+
+
+from transformers import DonutProcessor, VisionEncoderDecoderModel
+from datasets import load_dataset 
+import torch
+
+def get_attributes(input_img):
+    
+
+    access_token = os.environ.get('key')
+    processor = DonutProcessor.from_pretrained("AA-supply/donut-finetuned-lic-1", use_auth_token=access_token)
+    model = VisionEncoderDecoderModel.from_pretrained("AA-supply/donut-finetuned-lic-1", use_auth_token=access_token)
+
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+
+    model.eval()
+    model.to(device)
+        
+    pixel_values = processor(input_img, return_tensors="pt").pixel_values
+    pixel_values = pixel_values.to(device)
+    print(pixel_values.size())
+    # prepare decoder inputs
+    task_prompt = "<s_cord-v2>"
+    decoder_input_ids = processor.tokenizer(task_prompt, add_special_tokens=False, return_tensors="pt").input_ids
+    decoder_input_ids = decoder_input_ids.to(device)
+
+    # autoregressively generate sequence
+    outputs = model.generate(
+        pixel_values,
+        decoder_input_ids=decoder_input_ids,
+        max_length=model.decoder.config.max_position_embeddings,
+        early_stopping=True,
+        pad_token_id=processor.tokenizer.pad_token_id,
+        eos_token_id=processor.tokenizer.eos_token_id,
+        use_cache=True,
+        num_beams=1,
+        bad_words_ids=[[processor.tokenizer.unk_token_id]],
+        return_dict_in_generate=True,
+    )
+
+    # turn into JSON
+    seq = processor.batch_decode(outputs.sequences)[0]
+    seq = seq.replace(processor.tokenizer.eos_token, "").replace(processor.tokenizer.pad_token, "")
+    seq = re.sub(r"<.*?>", "", seq, count=1).strip()  # remove first task start token
+    seq = processor.token2json(seq)
+
+
+
+
+
+    return str(seq)
+
+demo = gr.Interface(get_attributes, "image", "label")
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+torch
+transformers
+numpy
+datasets