search

taesungp / swapping-autoencoder-pytorch

Official Implementation of Swapping Autoencoder for Deep Image Manipulation (NeurIPS 2020)
Other
512 stars 86 forks source link

Train own data set #15

Open Haosouth opened 2 years ago

Haosouth commented 2 years ago

Hello, thank you very much for your work, which has inspired me a lot. I would like to train my own data set based on your model training, but I don’t know much about some files in the data. If I If I want to train my own data set, should I copy cifar100_dataset.py or follow the way of unaligned.py? Also, the entry point for training is experiments, but I haven’t found any experiments package calling data package. What is going on, I hope I can answer it, thank you very much

Camillo4eyes commented 2 years ago

I also need this information

easm002 commented 1 year ago

Hello. It would be wonderful if we can train with our own dataset. Does anyone get solution? Many thanks

Haosouth commented 1 year ago

Hello. It would be wonderful if we can train with our own dataset. Does anyone get solution? Many thanks

I modified the image loading code in data/unaligned_dataset.py, the training is successful, you can try

easm002 commented 1 year ago

Hello. It would be wonderful if we can train with our own dataset. Does anyone get solution? Many thanks

I modified the image loading code in data/unaligned_dataset.py, the training is successful, you can try

Thank you so much Hao, I really appreciate it.