search

LWT3437 / LANet

Source Code for “LANet: A Luminance Attentive Network with Scale Invariance for HDR Image Reconstruction” (PG 2021)
16 stars 3 forks source link

LAM architecture #3

Open darthgera123 opened 2 years ago

darthgera123 commented 2 years ago

Hey @LWT3437 could you please share the network architecture for LAM. (the input and output channels for the various conv layers in LAM please) I am unable to understand it from the code

LWT3437 commented 2 years ago

@darthgera123 The network architecture of LAM has been shown in Figure 3 of the paper. The number of input and output channels of LAM are both 64. You can observe the changes of size and channels from the changes in the thickness and width of the rectangle. Specifically, the parameters in the deconv2d function ks (core size) and s (stride) indicate the output size and channels.