Benjamin Kurt Miller
Benjamin Kurt Miller
I think a bagging approach would likely be best.
> To avoid disabling all warnings, I changed `warnings.simplefilter("ignore")` in @shubhamkulkarni01's above solution to `warnings.filterwarnings("ignore", message=r"The feature ([^\s]+) is currently marked under review")` before importing `pl_bolts`. Works pretty well, but...
@janfb wanted to see a side-by-side comparison of the two with LayerNorm and BatchNorm before making the change.
I will follow up after Friday.
@janfb, I used `critic` since it was shorter than `discriminator`. Also `critic` is the name used in WGAN where the "discriminator" network does not act as a binary classifier. We...
okay, I'll follow your lead, but I would argue that maybe having one big change with many warnings will be simpler than adapting code once, then again for a later...
I literally just implemented this for another project. It shouldn't be too hard.
actually I will work on something else for now.
I also tried running my own "test" making sure to avoid using the GPU, just in case. However, it failed with a segmentation fault as well. ``` import tensorflow as...
> @mees I added support for that in #17163, if you want to give it a try. The PR only implements it for validation and testing. really helpful! I hope...