Sébastien Tosi

Thanks a lot for your reply! I had 1, 2 and 5 in mind but even then do you really believe that 3 and 4 could explain the remaining 30x...

Whatever the image and classifier, this macro runs fine: ``` CurrentImage = getTitle(); run("Segment Image With Labkit", "input="+CurrentImage+" segmenter_file=D:/Classifier.classifier use_gpu=1"); ``` while this doesn't (no output): ``` CurrentImage = getTitle();...

Actually, the problem seems more generic since other imglib based plugins returning results as virtual stacks suffer from a similar issue, or do not output anything. One example is Process...

@maarzt Thanks for looking into it. I have tried the new .jar. It works with a small glitch: in batch mode the image "output" generated by the plugin is not...

I see it by running another plugin right after exiting batch mode. Good practice is to select the image to process first, I agree, but this type of inconstitencies between...

Great! Thanks so much Martin! On Thu 17 Aug 2023, 21:09 Martin Drawitsch, ***@***.***> wrote: > Hello @SebastienTs , yes this is possible > with the regular torch.nn.CrossEntropyLoss by setting...

Thanks for elaborating on this topic! Since this is the only additional difference I could figure out between the UNet previously mentioned (with inverted ReLU / BN) and Elektronn3 UNet,...

Non multi-page TIFF would already be a great starting point! Do Part 3 (motion J2K) and Part 10 (3D data) have a straightforward HTJ2K extension and do you plan to...

Don't worry Osamu and good luck with the extreme weather. I hope that it will be better soon. On Tue, Aug 2, 2022, 06:44 Osamu Watanabe ***@***.***> wrote: > @SebastienTs...

Non multi-page TIFF would already be a great starting point! Do Part 3 (motion J2K) and Part 10 (3D data) have a straightforward HTJ2K extension and do you plan to...