Skip to main content

Table 3 Detailled architecture of UpscaleGAN \(32^{3}\rightarrow 64^{3}\). \(d=32\)

From: Cosmological N-body simulations: a challenge for scalable generative models

OperationParameter sizeOutput shape
Input borders (n,32,32,32,7)
Conv 3D (Sride 2)(4,4,4,7,d)(n,16,16,16,d)
Conv 3D (Sride 2)(4,4,4,d,d)(n,8,8,8,d)
Conv 3D (Sride 2)(4,4,4,d,16)(n,4,4,4,16)
Reshape (n,1024)
Input \(z_{1}\,\mathcal{N}(0,1)\) (n,1024)
Concatenation (n,2048)
Reshape (n,16,16,16,2)
Input downsampled corner (n,16,16,16,1)
Input \(z_{2} \mathcal{N}(0,1)\) (n,16,16,16,1)
Concatention (n,16,16,16,4)
TrConv 3D (Sride 1)(4,4,4,4,d)(n,16,16,16,d)
LReLu (α = 0.2) (n,16,16,16,4d)
TrConv 3D (Sride 1)(4,4,4,d,d)(n,16,16,16,d)
LReLu (α = 0.2) (n,16,16,16,2d)
TrConv 3D (Sride 2)(4,4,4,d,4d)(n,32,32,32,4d)
LReLu (α = 0.2) (n,32,32,32,4d)
TrConv 3D (Sride 1)(4,4,4,4d,2d)(n,32,32,32,2d)
LReLu (α = 0.2) (n,32,32,32,d)
TrConv 3D (Sride 1)(4,4,4,2d,1)(n,32,32,32,1)
Input generated image (n,32,32,32,1)
Input borders (n,32,32,32,7)
Reshape to a cube (n,64,64,64,1)
Input smooth image (n,64,64,64,1)
Concatenation (+ diff) (n,64,64,64,3)
Conv 3D (Sride 1)(4,4,4,3,d)(n,64,64,64,d)
LReLu (α = 0.2) (n,64,64,64,d)
Conv 3D (Sride 2)(4,4,4,d,2d)(n,32,32,32,2d)
LReLu (α = 0.2) (n,32,32,32,d)
Conv 3D (Sride 2)(4,4,4,2d,4d)(n,16,16,16,4d)
LReLu (α = 0.2) (n,16,16,16,d)
Conv 3D (Sride 1)(4,4,4,d,d)(n,16,16,16,d)
LReLu (α = 0.2) (n,16,16,16,d)
Conv 3D (Sride 2)(4,4,4,d,d)(n,8,8,8,d)
LReLu (α = 0.2) (n,8,8,8,d)
Reshape (n,512d)