Keep consistency in Classes ConvBNActivation (#3750)

* Keep consistency of ConvBNActivation

* Simplify using the Python3 idiom
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>
Co-authored-by: Vasilis Vryniotis <datumbox@users.noreply.github.com>

torchvision/models/mobilenetv2.py

@@ -46,7 +46,7 @@ class ConvBNActivation(nn.Sequential):
             norm_layer = nn.BatchNorm2d
         if activation_layer is None:
             activation_layer = nn.ReLU6
-        super(ConvBNReLU, self).__init__(
+        super().__init__(
             nn.Conv2d(in_planes, out_planes, kernel_size, stride, padding, dilation=dilation, groups=groups,
                       bias=False),
             norm_layer(out_planes),