Can we use multiple subjects for training?
nihaomiao opened this issue · 1 comments
nihaomiao commented
Hi, @carolineec Thanks for sharing your code! But I have some questions about your training dataset AlignedDataset (in the aligned_dataset.py).
It seems that it only allows using one subject for training. In this line of code, one can see that whether we have the next sample depends on the size of the dataset. So I guess that we can only use one subject for one training dataset. Is it correct? If we want to test it on another subject, we need to train the model again?
Thanks for your time!
Best
Haomiao
justinjohn0306 commented
Hi can you explain how you prepared your dataset? Like the folder tree?
…On Sat, Nov 28, 2020, 10:27 AM Haomiao Ni ***@***.***> wrote:
Hi, @carolineec <https://github.com/carolineec> Thanks for sharing your
code! But I have some questions about your training dataset AlignedDataset
(in the aligned_dataset.py).
It seems that it only allows using one subject for training. In this line
<https://github.com/carolineec/EverybodyDanceNow/blob/b094a6ab70071784d7aacd99063659c640ef7e76/data/aligned_dataset.py#L53>
of code, one can see that whether we have the next sample depends on the
size of the dataset. So I guess that we can only use one subject for one
training dataset. Is it correct? If we want to test it on another subject,
we need to train the model again?
Thanks for your time!
Best
Haomiao
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#8>, or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AIDVKQ3JJH2FYICZWNBVYELSSB7KFANCNFSM4UFRUKXA>
.