uddeshya

Training on all the digits at once

3

Hi, While training on multiple images of MNIST I was not getting any reasonable output upon **generation** of images, however when I trained on a single digit (say 3) I...

SCGM example in tutorial

6

Hi, I think there might be some flaw in the example uploaded, please correct me if I'm wrong. According to SCGM challenge, we had to segment the GREY MATTER. Here...

combined model loss

6

Hey, great work @hutec. I have a doubt though, in the paper "What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?", the loss function doesn't invoke the...

The initial generator pre-training using MSE loss is to initialize the weights properly?

high resolution images of dimension 96X96?

2

How did you get 96X96 high resolution REAL images for comparison? My understanding was that we take the original dataset (cifar-10, consisting images of dimension 32X32), down-sample the images to...

mone in generator

1

Hi, In the gan training code, since you have already used `gen_cost.backward(mone)` for generator, why are you still doing `gen_cost = -gen_cost` i.e, should it not be * just `gen_cost.backward(mone)`...

Assumptions on order size

1

Hi, In my understanding, here we are assuming that whenever the agent takes buying or selling action it is dealing with 1 unit of stock/FX, etc., right? And therefore while...

NER is a bit misleading (seems like named entity recognition) maybe change it to NRE