diff --git a/configs/_base_/models/ocrnet_r50-d8.py b/configs/_base_/models/ocrnet_r50-d8.py
index 52fe060b1..0f5ff956c 100644
--- a/configs/_base_/models/ocrnet_r50-d8.py
+++ b/configs/_base_/models/ocrnet_r50-d8.py
@@ -23,7 +23,7 @@ model = dict(
             channels=256,
             num_convs=1,
             concat_input=False,
-            drop_out_ratio=0.1,
+            dropout_ratio=0.1,
             num_classes=19,
             norm_cfg=norm_cfg,
             align_corners=False,
@@ -35,7 +35,7 @@ model = dict(
             in_index=3,
             channels=512,
             ocr_channels=256,
-            drop_out_ratio=0.1,
+            dropout_ratio=0.1,
             num_classes=19,
             norm_cfg=norm_cfg,
             align_corners=False,
diff --git a/demo/MMSegmentation_Tutorial.ipynb b/demo/MMSegmentation_Tutorial.ipynb
index 6ec7225dd..127ad4e6a 100644
--- a/demo/MMSegmentation_Tutorial.ipynb
+++ b/demo/MMSegmentation_Tutorial.ipynb
@@ -1031,7 +1031,7 @@
       "        in_index=3,\n",
       "        channels=512,\n",
       "        pool_scales=(1, 2, 3, 6),\n",
-      "        drop_out_ratio=0.1,\n",
+      "        dropout_ratio=0.1,\n",
       "        num_classes=8,\n",
       "        norm_cfg=dict(type='BN', requires_grad=True),\n",
       "        align_corners=False,\n",
@@ -1044,7 +1044,7 @@
       "        channels=256,\n",
       "        num_convs=1,\n",
       "        concat_input=False,\n",
-      "        drop_out_ratio=0.1,\n",
+      "        dropout_ratio=0.1,\n",
       "        num_classes=8,\n",
       "        norm_cfg=dict(type='BN', requires_grad=True),\n",
       "        align_corners=False,\n",
diff --git a/docs/config.md b/docs/config.md
index 595b8f977..d5c1cd9b6 100644
--- a/docs/config.md
+++ b/docs/config.md
@@ -66,7 +66,7 @@ model = dict(
         in_index=3,  # The index of feature map to select.
         channels=512,  # The intermediate channels of decode head.
         pool_scales=(1, 2, 3, 6),  # The avg pooling scales of PSPHead. Please refer to paper for details.
-        drop_out_ratio=0.1,  # The dropout ratio before final classification layer.
+        dropout_ratio=0.1,  # The dropout ratio before final classification layer.
         num_classes=19,  # Number of segmentation classs. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
         norm_cfg=dict(type='SyncBN', requires_grad=True),  # The configuration of norm layer.
         align_corners=False,  # The align_corners argument for resize in decoding.
@@ -81,7 +81,7 @@ model = dict(
         channels=256,  # The intermediate channels of decode head.
         num_convs=1,  # Number of convs in FCNHead. It is usually 1 in auxiliary head.
         concat_input=False,  # Whether concat output of convs with input before classification layer.
-        drop_out_ratio=0.1,  # The dropout ratio before final classification layer.
+        dropout_ratio=0.1,  # The dropout ratio before final classification layer.
         num_classes=19,  # Number of segmentation classs. Usually 19 for cityscapes, 21 for VOC, 150 for ADE20k.
         norm_cfg=dict(type='SyncBN', requires_grad=True),  # The configuration of norm layer.
         align_corners=False,  # The align_corners argument for resize in decoding.
diff --git a/docs/tutorials/new_modules.md b/docs/tutorials/new_modules.md
index 86f77f1e3..9832a30f0 100644
--- a/docs/tutorials/new_modules.md
+++ b/docs/tutorials/new_modules.md
@@ -168,7 +168,7 @@ model = dict(
         in_index=3,
         channels=512,
         pool_scales=(1, 2, 3, 6),
-        drop_out_ratio=0.1,
+        dropout_ratio=0.1,
         num_classes=19,
         norm_cfg=norm_cfg,
         align_corners=False,