for

[cebain]

hello，thanks for your revision very much。 I still want to ask a question。 We can see that the h5 file includes both image and label data， and when we train，for unlabeld data， we just extract volume batch which is the image data。 However， if I don't have labels of all data，I just have labels for some of the data, which really needs smei-supervise, then how should I write the h5 file, or I just read image for 2D pictures?

[supgy]

I also want to know how to make it, do you know what to do?

[cebain]

well，for data without labels, if you want to turn them into h5, you can simple write picture data as 'image', and for 'label' you can also write picture data or zero array or anything since 'label' for unlabeled data would not be read during the training process.

[supgy]

well，for data without labels, if you want to turn them into h5, you can simple write picture data as 'image', and for 'label' you can also write picture data or zero array or anything since 'label' for unlabeled data would not be read during the training process.

Thank you very much for your reply, which resolved my doubts, I will have a try. :)