PolarisT

Hi, could you please share where did you get the realtime-pytorch-CycleGAN project? Thanks a lot.

ok thanks! ------------------ 原始邮件 ------------------ 发件人: "junyanz/pytorch-CycleGAN-and-pix2pix" ***@***.***>; 发送时间: 2022年3月30日(星期三) 晚上10:10 ***@***.***>; ***@***.******@***.***>; 主题: Re: [junyanz/pytorch-CycleGAN-and-pix2pix] test_video.py returns error when loading video (Issue #1400) Hi, I got it from this repo: https://github.com/Vinno97/realtime-pytorch-CycleGAN-and-pix2pix Sorry for...

Hi! Maybe we can try to use this set(I used 2080Ti and it didn't went OOM ): 0: {'batch_size': 40, 'num_steps': 12, 'img_size': 32, 'batch_split': 2, 'gen_lr': 6e-5, 'disc_lr': 2e-4},...

Hi! I tried the settings below for CelebA (I used 2080Ti and it didn't went OOM ): 0: {'batch_size': 40, 'num_steps': 12, 'img_size': 32, 'batch_split': 2, 'gen_lr': 6e-5, 'disc_lr': 2e-4},...

Thanks a lot my friend. It seems like we just need to make a little change to the original code in user.py: line 64: self.model.load_state_dict(w_dict['state_dict'], strict=Ture) --> self.model.load_state_dict(w_dict['state_dict'], strict=False) line...

Thank you very much! @MaxChanger I just visualized the .label file generated by my method, but just as you said, it didn't load weight from the checkpoint and every point...

> > 非常感谢，这个解决方案对我来说是有效的 > > **我做了这个修改后，仍会报错，请问你是怎么解决此问题的** > > **修改点：**  > > **依然报错** Traceback (most recent call last): File "convert_weight.py", line 13, in from model import Generator, Discriminator File "/home/dan.wang/train_script/GAN/gan2shape/GAN2Shape/gan2shape/stylegan2/stylegan2-pytorch/model.py",...

Thanks so much for your answers. It helps me a lot! I have a question that will the PyTorch implementation of fused_leaky_relu affect the performance of the model or the...

I encounter the same problem, how to fix it?

You could add `self.pipe.to(self.device)` after `self.pipe = StableDiffusionPipeline.from_pretrained( self.cfg.pretrained_model_name_or_path, unet=unet, vae=vae, torch_dtype=self.weights_dtype, ).to(torch_dtype=self.weights_dtype, torch_device=self.device) ` which is in HumanGaussian/threestudio/models/guidance/dual_branch_guidance.py