Closed LukasStruppek closed 1 year ago
Hi Lukas,
Thank you for letting me know it. I have updated the config. It should be: "gan_file_path": "./datasets/celeba/meta/ganset.txt"
"dataset":{
"model_name": "VGG16",
"test_file_path": "./datasets/celeba/meta/testset.txt",
"gan_file_path": "./datasets/celeba/meta/ganset.txt",
"name": "celeba",
"img_path": "./datasets/celeba/img_align_celeba",
"img_gan_path": "./datasets/celeba/img_align_celeba",
"n_classes":1000,
"fid_real_path": "./datasets/celeba/meta/celeba_target_300ids.npy",
"KNN_real_path": "./datasets/celeba/meta/fea_target_300ids.npy",
"p_reg_path": "./checkpoints/p_reg"
},
Thanks. Ngoc
Hi Ngoc,
thank you very much for your fast response. It now seems to work – I just need to train two additional augmentation models.
Best, Lukas
Hi,
I am currently trying to reproduce the results from the paper. However, I am not able to run the LOMMA attack. However, it seems that a key (
gan_file_path
) is missing in the configuration file:And this is my configuration file:
Could you help me to fix this bug? I already tried adding the missing key with the value set to the generator path. Still, I receive another error for this. Thank you very much in advance :)
Best, Lukas