Kaan Bıçakcı

Check if softmax activation is used correctly

3

Feature request was made in #18909 This is a utility function to check if the usage of softmax makes sense (new users make this mistake a lot). Applying softmax on...

[Previous Feature Request] Throw an error if `softmax` is used incorrectly

4

I had a PR (#18105 - closed due to merging process) which was adding a utility function to the codebase if softmax is used with a 1 neuron as this...

Add get_config and from_config methods to DenseVariational_v2

2

Fixes the issue #1627: `NotImplementedError: Layer DenseVariational has arguments in __init__ and therefore must override get_config` Some unit tests are failing due to an internal issue in TF-Nightly as of...

Inconsistent implementations of RegNet between keras.applications and keras-cv

1

**Are you willing to contribute?**: Yes **Describe the problem**: Classification head implementations in keras-cv and keras.applications are different. From `keras.applications`: https://github.com/keras-team/keras/blob/fa5c889334c9821ebee1371417ba3bb02eec704d/keras/applications/regnet.py#L836-L854 ```python def Head(num_classes=1000, name=None): """Implementation of classification head of...