Ren Yurui
Ren Yurui
Hi! Is the checkpoint loaded successfully while inference? Can you provide the messages when you run inference.py
When you run `inference.py` without training the model. You may need to load the model by adding `--which_iter` such as: ``` bash python -m torch.distributed.launch \ --nproc_per_node=1 \ --master_port 12345...
> The url of pretrained model is broken? Could you please provide me a url to download the model? > Thank you ! Hi! The URL of Google Drive is...
> > > hello,I found that it does not exist of Script.PerceptualSimilarity.models in the repo.have you meet this trouble? > > > > > > hi ! Did you solve...
> the picture generated successfully but the texture is poor. What werid is that 6 month ago I've tested the pre-trained model and the generated pictures are OK. Recently I...
> > > > hello,I found that it does not exist of Script.PerceptualSimilarity.models in the repo.have you meet this trouble? > > > > > > > > > hi...
> > > the picture generated successfully but the texture is poor. What werid is that 6 month ago I've tested the pre-trained model and the generated pictures are OK....
Hi PangzeCheung, There is no specific reason for the choice. I think both of them are OK.
Hi Jarvisss, It seems that the difference is caused by the flow generator. Does the sampling correctness loss coverage after ~500k iters? I think training the flow generator for a...
Hi, Sorry for the delay. It seems that you build this module with windows. We only test the code with Linux. Thanks.