Joel Akeret

Hi @ChristmasLatte , hard to tell whats going on from what I see here. I'm currently working on a re-implementation of `tf_unet` that is based on tensorflow 2 & keras...

I could be that the training is not converging. How does the Tensorboard look like? Is the loss decreasing?

This is a known issue (#28) but unfortunately I haven't found a solution yet. Sorry for that

Hi thanks for this input. Which variables do mean exactly, could you point me to the relevant code line? The `variables` list is only used when [regularization](https://github.com/jakeret/tf_unet/blob/master/tf_unet/unet.py#L242) is used. Therefore...

Ok is see. Yes you're correct. Thank you for pointing this out. Those variables should be appended to the list. Weights and biases are indeed the ones updated by SGD....

Yes. However I don't know how big the effect is if they are in the list or not

Looks like a nice competition! - For I would check the Tensorboard. The loss should always be decreasing over the epochs. If not something might not be right (with the...

Out of curiosity: could you point us to this other repo?

I think you might be right. The values shouldn’t be hardcoded but rather derived from the parameters. I have to check how the filter size and the striding affects the...

You can send me a [pull request](https://help.github.com/articles/about-pull-requests/) so that I can merge your changes into the official repository