diff --git a/configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml b/configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml
index ab622d122c..ec03ba22db 100644
--- a/configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml
+++ b/configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml
@@ -23,7 +23,7 @@ Architecture:
   algorithm: DB
   Transform: null
   Backbone:
-    name: LCNetv3
+    name: PPLCNetV3
     scale: 0.75
     det: True
   Neck:
diff --git a/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml b/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml
index c104a39ec8..88217bc2fd 100644
--- a/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml
+++ b/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml
@@ -39,7 +39,8 @@ Architecture:
   algorithm: SVTR_LCNet
   Transform:
   Backbone:
-    name: LCNetv3
+    name: PPLCNetV3
+    scale: 0.95
   Head:
     name: MultiHead
     head_list:
diff --git a/ppocr/modeling/backbones/__init__.py b/ppocr/modeling/backbones/__init__.py
index 6dca38f1d9..873e8f6de1 100755
--- a/ppocr/modeling/backbones/__init__.py
+++ b/ppocr/modeling/backbones/__init__.py
@@ -22,11 +22,11 @@ def build_backbone(config, model_type):
         from .det_resnet_vd import ResNet_vd
         from .det_resnet_vd_sast import ResNet_SAST
         from .det_pp_lcnet import PPLCNet
-        from .rec_lcnetv3 import LCNetv3
+        from .rec_lcnetv3 import PPLCNetV3
         from .rec_hgnet import PPHGNet_small
         support_dict = [
             "MobileNetV3", "ResNet", "ResNet_vd", "ResNet_SAST", "PPLCNet",
-            "LCNetv3", "PPHGNet_small"
+            "PPLCNetV3", "PPHGNet_small"
         ]
         if model_type == "table":
             from .table_master_resnet import TableResNetExtra
@@ -48,13 +48,13 @@ def build_backbone(config, model_type):
         from .rec_resnet_rfl import ResNetRFL
         from .rec_densenet import DenseNet
         from .rec_shallow_cnn import ShallowCNN
-        from .rec_lcnetv3 import LCNetv3
+        from .rec_lcnetv3 import PPLCNetV3
         from .rec_hgnet import PPHGNet_small
         support_dict = [
             'MobileNetV1Enhance', 'MobileNetV3', 'ResNet', 'ResNetFPN', 'MTB',
             'ResNet31', 'ResNet45', 'ResNet_ASTER', 'MicroNet',
             'EfficientNetb3_PREN', 'SVTRNet', 'ViTSTR', 'ResNet32', 'ResNetRFL',
-            'DenseNet', 'ShallowCNN', 'LCNetv3', 'PPHGNet_small'
+            'DenseNet', 'ShallowCNN', 'PPLCNetV3', 'PPHGNet_small'
         ]
     elif model_type == 'e2e':
         from .e2e_resnet_vd_pg import ResNet
diff --git a/ppocr/modeling/backbones/rec_lcnetv3.py b/ppocr/modeling/backbones/rec_lcnetv3.py
index 8f3b0c560c..ab0951761d 100644
--- a/ppocr/modeling/backbones/rec_lcnetv3.py
+++ b/ppocr/modeling/backbones/rec_lcnetv3.py
@@ -372,7 +372,7 @@ class PPLCNetV3(nn.Layer):
             stride=2,
             lr_mult=self.lr_mult_list[0])
 
-        self.blocks2 = nn.Sequential(* [
+        self.blocks2 = nn.Sequential(*[
             LCNetV3Block(
                 in_channels=make_divisible(in_c * scale),
                 out_channels=make_divisible(out_c * scale),
@@ -382,11 +382,11 @@ class PPLCNetV3(nn.Layer):
                 conv_kxk_num=conv_kxk_num,
                 lr_mult=self.lr_mult_list[1],
                 lab_lr=lab_lr)
-            for i, (k, in_c, out_c, s, se) in enumerate(self.net_config[
-                "blocks2"])
+            for i, (k, in_c, out_c, s, se
+                    ) in enumerate(self.net_config["blocks2"])
         ])
 
-        self.blocks3 = nn.Sequential(* [
+        self.blocks3 = nn.Sequential(*[
             LCNetV3Block(
                 in_channels=make_divisible(in_c * scale),
                 out_channels=make_divisible(out_c * scale),
@@ -396,11 +396,11 @@ class PPLCNetV3(nn.Layer):
                 conv_kxk_num=conv_kxk_num,
                 lr_mult=self.lr_mult_list[2],
                 lab_lr=lab_lr)
-            for i, (k, in_c, out_c, s, se) in enumerate(self.net_config[
-                "blocks3"])
+            for i, (k, in_c, out_c, s, se
+                    ) in enumerate(self.net_config["blocks3"])
         ])
 
-        self.blocks4 = nn.Sequential(* [
+        self.blocks4 = nn.Sequential(*[
             LCNetV3Block(
                 in_channels=make_divisible(in_c * scale),
                 out_channels=make_divisible(out_c * scale),
@@ -410,11 +410,11 @@ class PPLCNetV3(nn.Layer):
                 conv_kxk_num=conv_kxk_num,
                 lr_mult=self.lr_mult_list[3],
                 lab_lr=lab_lr)
-            for i, (k, in_c, out_c, s, se) in enumerate(self.net_config[
-                "blocks4"])
+            for i, (k, in_c, out_c, s, se
+                    ) in enumerate(self.net_config["blocks4"])
         ])
 
-        self.blocks5 = nn.Sequential(* [
+        self.blocks5 = nn.Sequential(*[
             LCNetV3Block(
                 in_channels=make_divisible(in_c * scale),
                 out_channels=make_divisible(out_c * scale),
@@ -424,11 +424,11 @@ class PPLCNetV3(nn.Layer):
                 conv_kxk_num=conv_kxk_num,
                 lr_mult=self.lr_mult_list[4],
                 lab_lr=lab_lr)
-            for i, (k, in_c, out_c, s, se) in enumerate(self.net_config[
-                "blocks5"])
+            for i, (k, in_c, out_c, s, se
+                    ) in enumerate(self.net_config["blocks5"])
         ])
 
-        self.blocks6 = nn.Sequential(* [
+        self.blocks6 = nn.Sequential(*[
             LCNetV3Block(
                 in_channels=make_divisible(in_c * scale),
                 out_channels=make_divisible(out_c * scale),
@@ -438,8 +438,8 @@ class PPLCNetV3(nn.Layer):
                 conv_kxk_num=conv_kxk_num,
                 lr_mult=self.lr_mult_list[5],
                 lab_lr=lab_lr)
-            for i, (k, in_c, out_c, s, se) in enumerate(self.net_config[
-                "blocks6"])
+            for i, (k, in_c, out_c, s, se
+                    ) in enumerate(self.net_config["blocks6"])
         ])
         self.out_channels = make_divisible(512 * scale)
 
@@ -489,8 +489,3 @@ class PPLCNetV3(nn.Layer):
         else:
             x = F.avg_pool2d(x, [3, 2])
         return x
-
-
-def LCNetv3(scale=0.95, **kwargs):
-    model = PPLCNetV3(scale=scale, conv_kxk_num=4, **kwargs)
-    return model