Nikan Doosti

@xiaoyuhao1995 yes exactly.

@xiaoyuhao1995 Not really. First of all, CoarseNet is not working properly, literally taking an average filter over image would do same thing as CoarseNet is doing. Secondly, DetailsNet has not...

Please see commit https://github.com/Nikronic/CoarseNet/commit/a1a5300e3eaa5ca037e1385256a91176cf730139. ref: https://discuss.pytorch.org/t/about-normalization-using-pre-trained-vgg16-networks/23560/9 Furthermore, for test purposes on out 9 image subset, here is the mean and std values: `mean= [0.3918, 0.3725, 0.3191]` `std=[0.4881, 0.4835, 0.4661]`

Please see commit https://github.com/Nikronic/CoarseNet/commit/81a229fb5b8e3753331b9ab98e3d64b6924bd48c .

How to deal with halftone if our images are normalized???

VGG loss does not decrease at all: ```python ... 46 , 1 loss: 9.048758506774902 47 , 1 loss: 9.113825798034668 48 , 1 loss: 8.967781066894531 49 , 1 loss: 8.963032722473145 50...

@Sandy4321 Hi, I used the documentation and tutorials of `mlxtend` library itself. [Here](https://rasbt.github.io/mlxtend/user_guide/frequent_patterns/association_rules/) is the one. Also if you want to get into details [here](http://www.borgelt.net/eclat.html) you can find them. Bests

@Sandy4321 Sorry, do you mean a course or something like that? Acutally I think if you have good programming background and just want to extend your knowledge and gain a...

@Sandy4321 The point is association rule learning is a old topic which currently people do not use it because it fails and large scale problems. And one more thing you...

@Sandy4321 u just need to match notations with one the libraries. I do not think it's hard. The good part is there are examples in the slide so you can...