What is the method of selecting the model architectures?

kpandey008 / DiffuseVAE

Official implementation of "DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents"

MIT License

344 stars 32 forks source link

Open YuChen-Liang opened 10 months ago

YuChen-Liang commented 10 months ago

I want to reproduce it on MNIST and ImageNet, but I don't know how to choose the network architecture of the VAE. Do you have any suggestions?