Переделал рекурсию на цикл.

ppocr/data/simple_dataset.py

@@ -116,10 +116,25 @@ class SimpleDataSet(Dataset):
             ext_data.append(data)
         return ext_data
 
+    def create_dummy_sample(self):
+        """Создает пустой образец для предотвращения сбоев"""
+        dummy_img = np.zeros((32, 320, 3), dtype=np.uint8)
+        dummy_img = cv2.imencode('.jpg', dummy_img)[1].tobytes()
+        
+        return {
+            "image": dummy_img,
+            "label": "",
+            "img_path": "dummy.jpg",
+            "ext_data": self.get_ext_data(),
+            "filename": "dummy.jpg"
+        }
+
     def __getitem__(self, idx):
+        max_attempts = 10
+        for attempt in range(max_attempts):
+            try:
                 file_idx = self.data_idx_order_list[idx]
                 data_line = self.data_lines[file_idx]
-        try:
                 data_line = data_line.decode("utf-8")
                 substr = data_line.strip("\n").split(self.delimiter)
                 file_name = substr[0]
@@ -135,23 +150,23 @@ class SimpleDataSet(Dataset):
                 data["ext_data"] = self.get_ext_data()
                 data["filename"] = data["img_path"]
                 outs = transform(data, self.ops)
+                return outs
+
             except Exception as exc:
-            print("HERE", str(exc))
+                if attempt < max_attempts - 1:
-            self.logger.error(
+                    idx = (
-                "When parsing line {}, error happened with msg: {}".format(
-                    data_line, traceback.format_exc()
-                )
-            )
-            outs = None
-        if outs is None:
-            # during evaluation, we should fix the idx to get same results for many times of evaluation.
-            rnd_idx = (
                         np.random.randint(self.__len__())
                         if self.mode == "train"
                         else (idx + 1) % self.__len__()
                     )
-            return self.__getitem__(rnd_idx)
+
-        return outs
+                self.logger.error(
+                    "Failed after {} attempts: {}".format(
+                        max_attempts, str(exc)
+                    )
+                )
+
+                return self.create_dummy_sample()
 
     def __len__(self):
         return len(self.data_idx_order_list)