lizaitang

Thank you so much! By the way, can we achieve conditional GAN on FFHQ dataset?

Thanks, to achieve this do I need to retrain with the labels? Hzzone ***@***.***>于2022年9月30日 周五11:50写道： > Thank you so much! By the way, can we achieve conditional GAN on FFHQ...

> Please try models [here](https://github.com/NVlabs/stylegan/blob/03563d18a0cf8d67d897cc61e44479267968716b/metrics/linear_separability.py#L21). Thanks, I used this classfiers to test the result, but the prediction logits seems different each time, have you met the same issue?

Thanks, besides, during the generation process, I encounter a problem that "size mismatch for c_layers.4.layer.D: copying a param with shape torch.Size([512]) from checkpoint, the shape in current model is torch.Size([1,...

Thank you so much，so where should we add the one hot vector? right after the 18 features？