Переделал рекурсию на цикл.

ppocr/data/simple_dataset.py

@@ -116,42 +116,57 @@ 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):
-        file_idx = self.data_idx_order_list[idx]
+        max_attempts = 10
-        data_line = self.data_lines[file_idx]
+        for attempt in range(max_attempts):
-        try:
+            try:
-            data_line = data_line.decode("utf-8")
+                file_idx = self.data_idx_order_list[idx]
-            substr = data_line.strip("\n").split(self.delimiter)
+                data_line = self.data_lines[file_idx]
-            file_name = substr[0]
+                data_line = data_line.decode("utf-8")
-            file_name = self._try_parse_filename_list(file_name)
+                substr = data_line.strip("\n").split(self.delimiter)
-            label = substr[1]
+                file_name = substr[0]
-            img_path = os.path.join(self.data_dir, file_name)
+                file_name = self._try_parse_filename_list(file_name)
-            data = {"img_path": img_path, "label": label}
+                label = substr[1]
-            if not os.path.exists(img_path):
+                img_path = os.path.join(self.data_dir, file_name)
-                raise Exception("{} does not exist!".format(img_path))
+                data = {"img_path": img_path, "label": label}
-            with open(data["img_path"], "rb") as f:
+                if not os.path.exists(img_path):
-                img = f.read()
+                    raise Exception("{} does not exist!".format(img_path))
-                data["image"] = img
+                with open(data["img_path"], "rb") as f:
-            data["ext_data"] = self.get_ext_data()
+                    img = f.read()
-            data["filename"] = data["img_path"]
+                    data["image"] = img
-            outs = transform(data, self.ops)
+                data["ext_data"] = self.get_ext_data()
-        except Exception as exc:
+                data["filename"] = data["img_path"]
-            print("HERE", str(exc))
+                outs = transform(data, self.ops)
-            self.logger.error(
+                return outs
-                "When parsing line {}, error happened with msg: {}".format(
+
-                    data_line, traceback.format_exc()
+            except Exception as exc:
+                if attempt < max_attempts - 1:
+                    idx = (
+                        np.random.randint(self.__len__())
+                        if self.mode == "train"
+                        else (idx + 1) % self.__len__()
+                    )
+
+                self.logger.error(
+                    "Failed after {} attempts: {}".format(
+                        max_attempts, str(exc)
+                    )
                 )
-            )
+
-            outs = None
+                return self.create_dummy_sample()
-        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
 
     def __len__(self):
         return len(self.data_idx_order_list)