You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
it seems like activation[first_indices] has nan elements.
I used numpy.nan_to_num() to avoid the error, but will it affect my training effect?
I tried to run eval_t2m_vq.py following README, which means I was using the evaluation model downloaded from Google(given by the repo author), also got the same error, the call stack is:
The text was updated successfully, but these errors were encountered:
Keneyr
changed the title
"array must not contain infs or NaNs" when training vqvae
"array must not contain infs or NaNs" when training/evaluating vqvae
Mar 6, 2024
train_vq.py
, but got error likearray must not contain infs or NaNs
, the call stack is:it seems like
activation[first_indices]
hasnan
elements.I used
numpy.nan_to_num()
to avoid the error, but will it affect my training effect?eval_t2m_vq.py
followingREADME
, which means I was using the evaluation model downloaded from Google(given by the repo author), also got the same error, the call stack is:What should I do? Thank you!
The text was updated successfully, but these errors were encountered: