【styleGAN2ADA利用预训练模型搜索单张目标图像的W空间潜变量】

github:GitHub - NVlabs/stylegan2-ada: StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementationStyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation - GitHub - NVlabs/stylegan2-ada: StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementationhttps://github.com/NVlabs/stylegan2-ada

算法流程：

1.载入预训练style GAN2生成器网络，载入目标图像；

# Load networks.
print('Loading networks from "%s"...' % network_pkl)
device = torch.device('cuda')
with dnnlib.util.open_url(network_pkl) as fp:
    G = legacy.load_network_pkl(fp)['G_ema'].requires_grad_(False).to(device) # type: ignore
​
# Load target image.
target_pil = PIL.Image.open(target_fname).convert('