Kaan Bıçakcı

Results 11 comments of Kaan Bıçakcı

Hi @csuter, is there any chance that you can take a look at this tiny PR? Thanks.

> This is something that would make more sense in the `softmax` op, actually. Just check if `ops.shape[axis] == 1` and print a warning if so. So you mean completely...

Hi @divyashreepathihalli, Yes, I can create a new PR if you can confirm that this feature seems reasonable and that the Keras team would be willing to merge it. Thanks.

The implementation seems correct, but validation loss is sky-rocketing. I assume model is dealing with too extreme values and overfitting on training dataset. Can you remove the line: `outputs =...

Hmm this is strange, I checked the original Keras doc which has extreme loss values in validation too, so it will be hard to converge for a Bayesian NN. Can...

> I have the same problem about MaxPooling2D. The following tutorial about reproducibility of keras confirmed that the same error occurs: https://keras.io/examples/keras_recipes/reproducibility_recipes/ I wrote this guide when Keras had `jit_compile...

Hi @beyarkay, while waiting the Team's response let me provide some inputs. I think this requires much more effort rather than adding a simple assertion. Here are some of the...

@DeveshS215 I think the above gist is not complete as `entropy_sort_index` is not defined. Also it is not clear to me what `.item()` method should do in this case? Can...

@DeveshS215 I see, so if it is a scalar value, maybe you can employ some logic using `tf.reduce.xxx`.