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
Thank you for the repo! Upon reloading the Glow model from save after training, cross entropy performance diminished. This was likely because the ActNorm module was being reinitialized on the first input batch to a value the model didn't expect. I added a constructor flag to specify whether to reinitialize, and this seemed to fix the problem. I would imagine this is a larger issue for datasets with larger variance and smaller batch size.
Fix:
add an initialized flag to ActNorm constructor, set True when loading model
The text was updated successfully, but these errors were encountered:
Hello, thanks for your suggestions! I haved missed that cases...I fixed this at f332121 by changing initialized flag as module buffers. So it will be saved with model weights.
Thank you for the repo! Upon reloading the Glow model from save after training, cross entropy performance diminished. This was likely because the ActNorm module was being reinitialized on the first input batch to a value the model didn't expect. I added a constructor flag to specify whether to reinitialize, and this seemed to fix the problem. I would imagine this is a larger issue for datasets with larger variance and smaller batch size.
Fix:
The text was updated successfully, but these errors were encountered: