minor format adjustment

mmcv/cnn/__init__.py

@@ -4,7 +4,6 @@ from .resnet import ResNet, make_res_layer
 from .weight_init import xavier_init, normal_init, uniform_init, kaiming_init
 
 __all__ = [
-    'AlexNet', 'VGG', 'make_vgg_layer',
-    'ResNet', 'make_res_layer', 'xavier_init', 'normal_init', 'uniform_init',
-    'kaiming_init'
+    'AlexNet', 'VGG', 'make_vgg_layer', 'ResNet', 'make_res_layer',
+    'xavier_init', 'normal_init', 'uniform_init', 'kaiming_init'
 ]

mmcv/cnn/vgg.py

@@ -16,15 +16,10 @@ def conv3x3(in_planes, out_planes, dilation=1, bias=False):
         bias=bias)
 
 
-def make_vgg_layer(inplanes,
-                   planes,
-                   num_blocks,
-                   dilation=1,
-                   with_bn=False):
+def make_vgg_layer(inplanes, planes, num_blocks, dilation=1, with_bn=False):
     layers = []
     for _ in range(num_blocks):
-        layers.append(
-            conv3x3(inplanes, planes, dilation, not with_bn))
+        layers.append(conv3x3(inplanes, planes, dilation, not with_bn))
         if with_bn:
             layers.append(nn.BatchNorm2d(planes))
         layers.append(nn.ReLU(inplace=True))
@@ -118,9 +113,7 @@ class VGG(nn.Module):
             for m in self.modules():
                 if isinstance(m, nn.Conv2d):
                     nn.init.kaiming_normal_(
-                            m.weight,
-                            mode='fan_out',
-                            nonlinearity='relu')
+                        m.weight, mode='fan_out', nonlinearity='relu')
                     if m.bias is not None:
                         nn.init.constant_(m.bias, 0)
                 elif isinstance(m, nn.BatchNorm2d):