qingtian-k / VGG16

A PyTorch implementation of VGG16. This could be considered as a variant of the original VGG16 since BN layers are added after each conv. layer

VGG16

an implementation of VGG16 in pytorch. VGG16 architecture is well depicted in the following image:

image source : https://blog.heuritech.com/2016/02/29/a-brief-report-of-the-heuritech-deep-learning-meetup-5/

modified (batch norm. added in each cnn layer)

        # 1-1 conv layer
        tnn.Conv2d(3, 64, kernel_size=3, padding=1),
        tnn.BatchNorm2d(64),
        tnn.ReLU(),

        # 1-2 conv layer
        tnn.Conv2d(64, 64, kernel_size=3, padding=1),
        tnn.BatchNorm2d(64),
        tnn.ReLU(),