Update inference.py

inference.py

@@ -16,24 +16,6 @@ model.to(device)
 
 import json
 
-
-# Funzione per creare l'output JSON in formato CORD-like
-def create_json_output(words, labels, boxes):
-    output = []
-    
-    for word, label, box in zip(words, labels, boxes):
-        # Considera solo le etichette rilevanti (escludendo "O")
-        if label != "O":
-            output.append({
-                "text": word,
-                "category": label,  # la categoria predetta dal modello (es. "B-PRODUCT", "B-PRICE", "B-TOTAL")
-                "bounding_box": box  # le coordinate di bounding box per la parola
-            })
-    
-    # Converti in JSON
-    json_output = json.dumps(output, indent=4)
-    return json_output
-
 def prediction(image):
 
     boxes, words = OCR(image)
@@ -55,8 +37,41 @@ def prediction(image):
     token_boxes = encoding.bbox.squeeze().tolist()
     probabilities = torch.softmax(outputs.logits, dim=-1)
     confidence_scores = probabilities.max(-1).values.squeeze().tolist()
-    # Crea il JSON usando i risultati ottenuti
-    json_result = create_json_output(words, labels, boxes)
+
+    inp_ids = encoding.input_ids.squeeze().tolist()
+    inp_words = [tokenizer.decode(i) for i in inp_ids]
+
+    width, height = image.size
+    is_subword = np.array(offset_mapping.squeeze().tolist())[:, 0] != 0
+
+    true_predictions = [id2label[pred] for idx, pred in enumerate(predictions) if not is_subword[idx]]
+    true_boxes = [unnormalize_box(box, width, height) for idx, box in enumerate(token_boxes) if not is_subword[idx]]
+    true_confidence_scores = [confidence_scores[idx] for idx, conf in enumerate(confidence_scores) if not is_subword[idx]]
+    true_words = []
+
+    for id, i in enumerate(inp_words):
+        if not is_subword[id]:
+            true_words.append(i)
+        else:
+            true_words[-1] = true_words[-1]+i
+
+    true_predictions = true_predictions[1:-1]
+    true_boxes = true_boxes[1:-1]
+    true_words = true_words[1:-1]
+    true_confidence_scores = true_confidence_scores[1:-1]
+
+    d = {}
+    for id, i in enumerate(true_predictions):
+        #rimuovo i prefissi
+        if i != "O":
+            i = i[2:]
+        if i not in d.keys():
+            d[i] = true_words[id]
+        else:
+            d[i] = d[i] + ", " + true_words[id]
+    d = {k: v.strip() for (k, v) in d.items()}
+
+    if "O" in d: d.pop("O")
 
     draw = ImageDraw.Draw(image, "RGBA")
     font = ImageFont.load_default()
@@ -65,5 +80,5 @@ def prediction(image):
             draw.rectangle(box)
             draw.text((box[0]+10, box[1]-10), text=str(prediction)+ ", "+ str(confidence), font=font, fill="black", font_size="15")
     
-    return image, json_result
+    return image, d