Tilak

@gowthamkpr, I was able to reproduce the issue on tensorflow v2.8, v2.9 and nightly. Kindly find the gist of it [here](https://colab.research.google.com/gist/tilakrayal/edc5936e8c247cf0df328421c1dd685d/untitled568.ipynb).

@adriangb, I tried t o execute the mentioned code on the latest tensorflow v2.18 and observed that it was executed without fail/error. Kindly find the gist of it [here](https://colab.research.google.com/gist/tilakrayal/544fe76081b2aa8ab01a75a6cb1edb50/untitled2383.ipynb). Thank...

@gowthamkpr, I was able to reproduce the issue on tensorflow v2.8 and nightly. Kindly find the gist of it [here](https://colab.research.google.com/gist/tilakrayal/66633ac47fb53276aa04675ad751007a/frost_is_tf_issue.ipynb).

@princyiakov, Code shared is full of [indentation errors](https://colab.research.google.com/gist/tilakrayal/4e00f3af2f2b18ad87f07c7b18a7d1d1/untitled645.ipynb), please share a colab gist with issue reported or simple stand alone indented code with all dependencies such that we can replicate...

@gowthamkpr, I was able to reproduce the issue on tensorflow v2.8, v2.10 and nightly. Kindly find the gist of it [here](https://colab.research.google.com/gist/tilakrayal/8828dbea3e51cf6a3af800aa05c10730/untitled653.ipynb).

@gowthamkpr, I was able to reproduce the issue in tensorflow v2.9 and nightly. Kindly find the gist of it [here](https://colab.research.google.com/gist/tilakrayal/4e05333c569edb6b0ccc002798f5ecff/untitled689.ipynb).

@rakshithvsk, Could you please elaborate about your Feature. Also, please specify the Use Cases for this feature. Thank you!

@gowthamkpr, I was able to reproduce the issue on tensorflow v2.9, v2.11 and nightly. Kindly find the gist of it [here](https://colab.research.google.com/gist/tilakrayal/e194dcc44dbf610487087dca2ca1ef8d/untitled772.ipynb).

@jamesbraza, There are changes happened in latest Keras3.0 version, where the weights are saved and loaded must end by using .**weights.h5** format. https://keras.io/api/models/model_saving_apis/weights_saving_and_loading/#save_weights-method I tried with the same format and...

@CV-42, When working with large input values, calculations within the **BinaryFocalCrossEntropy** function can lead to numerical overflow. This occurs when the intermediate results during computation exceed the range of the...