add logging

app.py

@@ -12,10 +12,13 @@ def process_filename(filename, question):
 
 
 def process_image(image, question):
-    processor = DonutProcessor.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
-    model = VisionEncoderDecoderModel.from_pretrained("naver-clova-ix/donut-base-finetuned-docvqa")
+    repo_id = "naver-clova-ix/donut-base-finetuned-docvqa"
+    print(f"Model repo: {repo_id}")
+    processor = DonutProcessor.from_pretrained(repo_id)
+    model = VisionEncoderDecoderModel.from_pretrained(repo_id)
 
     device = "cuda" if torch.cuda.is_available() else "cpu"
+    print(f"Device used: {device}")
     model.to(device)
 
     # prepare decoder inputs
@@ -35,6 +38,9 @@ def process_image(image, question):
         return_dict_in_generate=True,
     )
 
+    print(outputs)
+    print(outputs.sequences)
+
     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