Skip to main content

Table 2 Detailled architecture of the low resolution GAN \(0\rightarrow 32^{3}\). \(d=64\)

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

Operation

Parameter size

Output Shape

 

Generator

Input \(z\,\mathcal{N}(0,1)\)

 

(n,256)

Dense

(256,256d)

(n,256d)

Reshape

 

(n,4,4,4,4d)

TrConv 3D (Sride 2)

(4,4,4,4d,4d)

(n,8,8,8,4d)

LReLu (α = 0.2)

 

(n,16,16,16,4d)

TrConv 3D (Sride 2)

(4,4,4,4d,2d)

(n,16,16,16,2d)

LReLu (α = 0.2)

 

(n,16,16,16,2d)

TrConv 3D (Sride 2)

(4,4,4,d,d)

(n,32,32,32,d)

LReLu (α = 0.2)

 

(n,32,32,32,2d)

TrConv 3D (Sride 1)

(4,4,4,d,d)

(n,32,32,32,d)

LReLu (α = 0.2)

 

(n,32,32,32,2d)

TrConv 3D (Sride 1)

(4,4,4,d,1)

(n,32,32,32,1)

 

Discriminator

Input generated image

 

(n,32,32,32,1)

Conv 3D (Sride 2)

(4,4,4,1,d)

(n,32,32,32,d)

LReLu (α = 0.2)

 

(n,32,32,32,d)

Conv 3D (Sride 2)

(4,4,4,d,d)

(n,32,32,32,d)

LReLu (α = 0.2)

 

(n,32,32,32,d)

Conv 3D (Sride 1)

(4,4,4,d,2d)

(n,16,16,16,2d)

LReLu (α = 0.2)

 

(n,16,16,16,2d)

Conv 3D (Sride 1)

(4,4,4,2d,4d)

(n,8,8,8,4d)

LReLu (α = 0.2)

 

(n,8,8,8,4d)

Conv 3D (Sride 1)

(4,4,4,4d,8d)

(n,4,4,4,8d)

LReLu (α = 0.2)

 

(n,4,4,4,8d)

Reshape

 

(n,512d)

Dense

(512d,1)

(n,1)