Added annotation typing to vgg (#2861)

* style: Added annotation typing for vgg

* fix: Fixed annotation typing

* refactor: Removed un-necessary import

* fix: Added missing annotation for kwargs

* fix: Fixed constructor typing

* refactor: Refactored typing to minize changes

* refactor: Refactored typing cast

* fix: Fixed module list typing

torchvision/models/vgg.py

 import torch
 import torch.nn as nn
 from .utils import load_state_dict_from_url
+from typing import Union, List, Dict, Any, cast
 
 
 __all__ = [
@@ -23,7 +24,12 @@ model_urls = {
 
 class VGG(nn.Module):
 
-    def __init__(self, features, num_classes=1000, init_weights=True):
+    def __init__(
+        self,
+        features: nn.Module,
+        num_classes: int = 1000,
+        init_weights: bool = True
+    ) -> None:
         super(VGG, self).__init__()
         self.features = features
         self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
@@ -39,14 +45,14 @@ class VGG(nn.Module):
         if init_weights:
             self._initialize_weights()
 
-    def forward(self, x):
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
         x = self.features(x)
         x = self.avgpool(x)
         x = torch.flatten(x, 1)
         x = self.classifier(x)
         return x
 
-    def _initialize_weights(self):
+    def _initialize_weights(self) -> None:
         for m in self.modules():
             if isinstance(m, nn.Conv2d):
                 nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
@@ -60,13 +66,14 @@ class VGG(nn.Module):
                 nn.init.constant_(m.bias, 0)
 
 
-def make_layers(cfg, batch_norm=False):
-    layers = []
+def make_layers(cfg: List[Union[str, int]], batch_norm: bool = False) -> nn.Sequential:
+    layers: List[nn.Module] = []
     in_channels = 3
     for v in cfg:
         if v == 'M':
             layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
         else:
+            v = cast(int, v)
             conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
             if batch_norm:
                 layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
@@ -76,7 +83,7 @@ def make_layers(cfg, batch_norm=False):
     return nn.Sequential(*layers)
 
 
-cfgs = {
+cfgs: Dict[str, List[Union[str, int]]] = {
     'A': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
     'B': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
     'D': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
@@ -84,7 +91,7 @@ cfgs = {
 }
 
 
-def _vgg(arch, cfg, batch_norm, pretrained, progress, **kwargs):
+def _vgg(arch: str, cfg: str, batch_norm: bool, pretrained: bool, progress: bool, **kwargs: Any) -> VGG:
     if pretrained:
         kwargs['init_weights'] = False
     model = VGG(make_layers(cfgs[cfg], batch_norm=batch_norm), **kwargs)
@@ -95,7 +102,7 @@ def _vgg(arch, cfg, batch_norm, pretrained, progress, **kwargs):
     return model
 
 
-def vgg11(pretrained=False, progress=True, **kwargs):
+def vgg11(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 11-layer model (configuration "A") from
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -106,7 +113,7 @@ def vgg11(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg11', 'A', False, pretrained, progress, **kwargs)
 
 
-def vgg11_bn(pretrained=False, progress=True, **kwargs):
+def vgg11_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 11-layer model (configuration "A") with batch normalization
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -117,7 +124,7 @@ def vgg11_bn(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg11_bn', 'A', True, pretrained, progress, **kwargs)
 
 
-def vgg13(pretrained=False, progress=True, **kwargs):
+def vgg13(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 13-layer model (configuration "B")
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -128,7 +135,7 @@ def vgg13(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg13', 'B', False, pretrained, progress, **kwargs)
 
 
-def vgg13_bn(pretrained=False, progress=True, **kwargs):
+def vgg13_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 13-layer model (configuration "B") with batch normalization
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -139,7 +146,7 @@ def vgg13_bn(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg13_bn', 'B', True, pretrained, progress, **kwargs)
 
 
-def vgg16(pretrained=False, progress=True, **kwargs):
+def vgg16(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 16-layer model (configuration "D")
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -150,7 +157,7 @@ def vgg16(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg16', 'D', False, pretrained, progress, **kwargs)
 
 
-def vgg16_bn(pretrained=False, progress=True, **kwargs):
+def vgg16_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 16-layer model (configuration "D") with batch normalization
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -161,7 +168,7 @@ def vgg16_bn(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg16_bn', 'D', True, pretrained, progress, **kwargs)
 
 
-def vgg19(pretrained=False, progress=True, **kwargs):
+def vgg19(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 19-layer model (configuration "E")
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_
 
@@ -172,7 +179,7 @@ def vgg19(pretrained=False, progress=True, **kwargs):
     return _vgg('vgg19', 'E', False, pretrained, progress, **kwargs)
 
 
-def vgg19_bn(pretrained=False, progress=True, **kwargs):
+def vgg19_bn(pretrained: bool = False, progress: bool = True, **kwargs: Any) -> VGG:
     r"""VGG 19-layer model (configuration 'E') with batch normalization
     `"Very Deep Convolutional Networks For Large-Scale Image Recognition" <https://arxiv.org/pdf/1409.1556.pdf>`_