search

rosinality / vq-vae-2-pytorch

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch
Other
1.6k stars 270 forks source link

How To Generate Images #29

Closed impulsecorp closed 4 years ago

impulsecorp commented 4 years ago

What command do I run to generated images using your pretrained model? I tried various methods such as python3 sample.py --vqvae --top test.jpg but could not figure it out.

TWJubb commented 4 years ago

Try

python3 sample.py --batch=32 --top=pixelsnail_top_<N>.pt --bottom=pixelsnail_bottom_<N>.pt --vqvae=vqvae_<N>.pt test.jpg

where you replace <N> with the relevant number; pointing these arguments to the checkpoint of three models you've trained to get to this point.

WoshiBoluo commented 3 years ago

Try

python3 sample.py --batch=32 --top=pixelsnail_top_<N>.pt --bottom=pixelsnail_bottom_<N>.pt --vqvae=vqvae_<N>.pt test.jpg

where you replace <N> with the relevant number; pointing these arguments to the checkpoint of three models you've trained to get to this point.

Hi, how to generate images just using vqvae1 ?