convNet.pytorch icon indicating copy to clipboard operation
convNet.pytorch copied to clipboard

bug in vgg?

Open rosenfeldamir opened this issue 5 years ago • 0 comments

Hi, cool framework! note that you add a layer of AvgPool2D with kernel=1 in the class VGG. This basically doesn't have any effect. Perhaps you meant AdaptiveAveragePool? In addition, the input for the classification layer is usually 77512, given an input of 224x224.

rosenfeldamir avatar May 17 '19 16:05 rosenfeldamir