Harsha

more succintly `FL(all samples) = FL(pos samples) + FL(neg samples) ...`

`pos samples` itself means `y = 1`. So, `y * FL(pos samples)` again is redundant. Regarding why `FL (all samples) = FL (pos samples) - FL(neg samples)`, Section 2.1 from...

@dmrangak Did you look into the `tf.train.load_checkpoint` function?

upon further thinking, it is probably best to leave the hard-coded elements as is because the idea was to present the originally published models as is rather than make them...

I presume you trained a model on mouse brains. Correct? Let's take a step back and understand if the basic u-net model (or meshnet) described in the guide will perform...

@araikes thanks for checking. I will get to this later today or tomorrow. Working on fixing other related issues.

@araikes Can you please email me at hvgazula AT umich DOT edu to set up a call to discuss this so I can take it further? Thanks.

Try 50, please. The cluster on my end is down, so I am stuck a bit on this. :/

Could you tell what the error is?

- [x] setup kwyk data - [x] unet model (nobrainer library model) - [x] unet model (standard tf model) - [x] environment setup - [x] training on dgx-100 (volta) --...