Help! mistakes in dataloader

[Alienfoxz]

1. I guess this should be train+val+test, otherview, I got empty train dataset
   

   FaceDiffuser/data_loader.py

   Line 62 in b1f386f

   all_subjects = args.test_subjects.split() + args.val_subjects.split() + args.test_subjects.split()

2. wrong key building for one hot generation
   

   FaceDiffuser/data_loader.py

   Lines 31 to 33 in b1f386f

   	if self.data_type == "train":
   	subject = file_name.split("_")[0]
   	one_hot = self.one_hot_labels[self.subjects_dict["train"].index(subject)]

[Alienfoxz]

moreover, could any one help me getting "weighted_mouth_mask.txt" and "forehead_mask.txt" . They are not in regions folder after data processing.

[HiouKaoru]

Unfortunately, I have encountered the same problem as you, and I would like to know if you have found a solution

[Jackson-coder]

@Alienfoxz @Hozumi-z Just modify the dataloader.py ! The code in Line 62 should be all_subjects = args.train_subjects.split() + args.val_subjects.split() + args.test_subjects.split() and the code in Line 32 should be subject = "_".join(file_name.split("_")[:-1]).

[HiouKaoru]

@Alienfoxz @Hozumi-z Just modify the dataloader.py ! The code in Line 62 should be all_subjects = args.train_subjects.split() + args.val_subjects.split() + args.test_subjects.split() and the code in Line 32 should be subject = "_".join(file_name.split("_")[:-1]).

Thank you！
And I have another question. I followed the instructions to process the downloaded the training data of vocaset and obtained an incomplete sequence. For example, I am missing FaceTalk_170809_00138-TA_sentence32.npy. I was wondering if you could help me.