Where to set the labels used for training, such as 1/2, 1/4

HUANGLIZI / LViT

[IEEE Transactions on Medical Imaging/TMI] This repo is the official implementation of "LViT: Language meets Vision Transformer in Medical Image Segmentation"

MIT License

283 stars 26 forks source link

Where to set the labels used for training, such as 1/2, 1/4 #40

Closed acmername closed 6 months ago

acmername commented 6 months ago

Looking forward to your reply Thanks！

HUANGLIZI commented 6 months ago

Please use train_dataset, test_dataset = torch.utils.data.random_split(full_dataset, [train_size, test_size]) to split the dataset, and the random seed is the same as others.

acmername commented 6 months ago

Thank you for your timely recovery. Do you mean take half img and half labelcol from Train_Floder in the dataset file, subtract the corresponding data from train_text.xlsx and train?