Trouble understanding Fully-Convolution Network

Layer 7 is just the last convolutional layer of VGG16.

Layer 8 would be a fully connected/dense layer, but instead is replaced with a 1×1 convolution which, if input to this layer would be of size 1×1, is the same thing. Otherwise its as if you mapped each pixel through the same dense layer.

If your input size is such that input to layer 8 is of size 1×1, then there is no difference. If its bigger, this still potentially allows the network to work in a meaningful way.

CLICK HERE to find out more related problems solutions.

Leave a Comment

Your email address will not be published.

Scroll to Top