Daniil Pakhomov

@coolcoder001 @superoil1983 @sharanry -- that's a bug that appeared after the new version of pytorch came out. Will resolve it soon. Thank you for reporting guys :)

@coolcoder001 @superoil1983 @sharanry I have just checked the file ```resnet_34_8s_benchmark``` with pytorch version of ```0.3.1``` and python 2 installed in anaconda 2 and it seems to work fine. Could you...

I have also checked it on the latest unstable version of pytorch and python2 -- it works. My hypothesis is that this problem is related to python 3 which we...

Hi @nayriz . Thank you for reporting. That's a bug, change this line in your notebook: ``` logits_flatten = flatten_logits(logits, number_of_classes=21) ``` In your case, ```number_of_classes=2``` Let me know if...

Did that help to resolve your problem? You should change everything related to number of classes. Also check this file: https://github.com/warmspringwinds/pytorch-segmentation-detection/blob/master/pytorch_segmentation_detection/recipes/endovis_2017/segmentation/resnet_18_8s_train.ipynb It's a training file for a different dataset where...

Great! Try it out. Also bear in mind that your labels should be 0 and 1 (background and your class) in the annotations and 255 for regions that you want...

@nayriz I mean that depending on the number of classes in your own dataset you should change all the related variables. Yes, in Endovis we did it with 2 classes...

Basically, this method is very similar to usual Hessian. But on the coins data is shows better results. (examples are taken from source code examples) Hessian:  Hessian-Laplace:  But...

Dear community. Could you, please, give me a hint on what to do next. Because later I won't have much time and I am afraid that I won't be able...

@vighneshbirodkar I made a thorough research and found out that Hessian-Laplace method actually works worse than a usual method based on Determinant of Hessian. This is because determinant of Hessian...