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
Some people have had the issue of images not augmenting in notebook 05.
You can see the issue on the course GitHub here: #350
This is because of a recent update on how augmentation layers work in TensorFlow 2.8.
A fix should be on the way from the TensorFlow team but for now, one way to fix it is to make sure the parameter training=True is passed to a data augmentation model.
This is because data augmentation is only intended to work during training and not testing.
Code before
augmented_img = data_augmentation(img)
Doing this would result in images sometimes not being augmented (changed).
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Some people have had the issue of images not augmenting in notebook 05.
You can see the issue on the course GitHub here: #350
This is because of a recent update on how augmentation layers work in TensorFlow 2.8.
A fix should be on the way from the TensorFlow team but for now, one way to fix it is to make sure the parameter
training=True
is passed to a data augmentation model.This is because data augmentation is only intended to work during training and not testing.
Code before
Doing this would result in images sometimes not being augmented (changed).
Code after the fix
You should see your images slightly change after running this line (as well as the rest of the code in the video).
You can see a notebook example of this in action here: https://colab.research.google.com/drive/1qhCnJZgYAPzSnjq-PhB4fM5CtvqS34UP?usp=sharing
Beta Was this translation helpful? Give feedback.
All reactions