sneh-debug

> Hi, I’m having trouble training and the dice coefficient never goes higher than .03 I’m using BRATS 2018 without any modifications of the data, and also how do you...

> > > doc78, thanks for your feedback. I do not understand the logic for seeing "nan" values. That usually happens when your feeding bad values into something like an...

> > > my dice score is 0.35-0.37 > > > > > > how did you do that ? can you help me on finding predicted value for it...

1-dice_coefficient or -dice_coeffficient makes no difference for convergence 1-dice_coef just more familiar for monitoring as its value belong to [0, 1], not [-1, 0] On Tue, Feb 25, 2020 at...

> I have try from 5-200 epoch even though dice score range from 0.00-0.2 not more than that > […](#) > On Tue, 25 Feb 2020, 12:29 sneh-debug, ***@***.***> wrote:...

ok.. maybe there is something missing in the code. I am also working on it! On Fri, Feb 28, 2020 at 8:56 PM bhagi369 wrote: > I have try from...

> > ok.. maybe there is something missing in the code. I am also working on it! > > […](#) > > On Fri, Feb 28, 2020 at 8:56 PM...

@bhagi369 have you tried bigger patch size?

@shaleenanuj Please tell me the dependency of tensorflow and keras you have installed to run this code?

2D data