add comments for the modified implementation of ResNet (#1983)

Co-authored-by: Charles Pao <dirtybluer@gmail.com>

torchvision/models/resnet.py

@@ -73,6 +73,12 @@ class BasicBlock(nn.Module):
 
 
 class Bottleneck(nn.Module):
+    # Bottleneck in torchvision places the stride for downsampling at 3x3 convolution(self.conv2)
+    # while original implementation places the stride at the first 1x1 convolution(self.conv1)
+    # according to "Deep residual learning for image recognition"https://arxiv.org/abs/1512.03385.
+    # This variant is also known as ResNet V1.5 and improves accuracy according to
+    # https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch.
+
     expansion = 4
 
     def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,