GuohongWu

Why don't you use BatchNorm layers in training nets?

3

In CenterFace and your SphereFace, your net models are both based on ResNets. But I noticed that neither of you use any BatchNorm layers (which differ from original resnets). I...

Lack of two hyper-parameters for 'DenseNet-BC' support?

1

I have carefully read the authors' original paper. they mention their DenseNet-BC as a composition of 'DenseNet-B' and 'DenseNet-C' (see paper's sec-3 'Bottleneck layers' & 'Compression'). In 'DenseNet-B', a hyper-parameter...