Dominik Müller

Hey @ssean819, > But when I try to install miscnn1.1.0. It seems missing some files. You are right. The wheel was missing on PyPI for some reasons :O I uploaded...

Hi @ssean819, you are correct. This is a Tensorflow issue. Sadly I'm unfamiliar with this error. Nevertheless, these two issues suggest that it could has something to do with: -...

@tslee69, seems like tensorflow added some more issues since version 2.4.0 to its multi-gpu support for keras :/ Check out this: - https://stackoverflow.com/questions/65322700/tensorflow-keras-consider-either-turning-off-auto-sharding-or-switching-the-a - https://github.com/tensorflow/tensorflow/commit/92bd8e1034086d28b7e47d1a523caa452bacd06a

Heyho MichaelLempart, would it be possible that you provide a reproducible example for me? It could be related to your batch size. If during training, your number of samples are...

Thank you. I will try to reproduce it. When look at it, I would say that the configuration are looking absolutely fine and shouldn't throw an error.

Hey @MichaelLempart, sadly, I was not able to reproduce the error message with your provided code. Would it be possible that you provide an error log? Also really helpful would...

Discussed in #73. Implemented by @JimHeo, @Deathlymad & @muellerdo. Finalized in 998d6f5392e50f8b9285cd09b2d8b25de9e8ca3d.

Hello @anirban1513, thanks for pointing out this issue. Could you check out the newest MIScnn version and validate the created NIfTI predictions are now loadable in 3rd party applications like...

Heyho MichaelLempart, it works as expected, even though I have to admit that the naming is not the most intuitive. ;) **The intention behind it:** I wanted to created an...

> yes, I noticed that the cropping and augmentation can become a huge bottleneck when training on the fly. Maybe some multiprocessing could increase the performance. Currently, the SingleThreaded interface...