Frédéric Branchaud-Charron
Frédéric Branchaud-Charron
Unfortunatly, the last Keras community meeting was cancelled due to TF Summit, I'll raise this issue during the next one. Sorry for the delay.
With the new API, this could be done using a K.switch right?
Could we have a notebook/example script in a new folder that showcase this method?
Hello! This [commit](https://github.com/keras-team/keras-preprocessing/commit/9a836c25177e1be5940e1b2ab19fdb383225c32a#diff-d16be738737f6fddf4ab05a2d02ef21a) seems to be the issue. I can fix it tomorrow, but PRs are welcome :)
Oh right, I cannot merge the PR myself. Would anyone be available to make a PR? The diff is in #294 .
This will be added to the list of issues needed to be fixed when we will work on the refactoring. (See https://github.com/keras-team/governance/pull/10 for updates)
Switching to tf_addons is a pretty big change so I will reach out to Francois. Thank you for the PR!
Once tensorflow/tensorflow#46637 is merged I think we can merge this pr. Thank you!
Hello, With ZCA whitening not being as popular as at the beginning of Deep learning, I don't think we should include this in Keras-prepro. I'm open to discussion :)
This is quite hidden into the code base, but in the case of flow_from_directory, it is a percentage per directory. https://github.com/keras-team/keras-preprocessing/blob/daadd519238b19cdd8ffc962a99b25ee40368462/keras_preprocessing/image/utils.py#L195