aleju / papers Goto Github PK
View Code? Open in Web Editor NEWSummaries of machine learning papers
Summaries of machine learning papers
Hi @aleju ,
A big thank you for the summary of the PG-Gan paper. I am trying to understand this method and your repository was really helpful!
I have a question, and I was wondering if I can get your thoughts: The paper mentions that their training is unsupervised - meaning that it was not label-conditioned. Then how come they were able to generate label-specific images for LSUN dataset? Did they train separate networks for each label or is their network a multi-class generator?
Thanks in advance!
This is useful for objects where no object parts are locally in the corners (e.g. imagine a frontal-view on a human with stretched out arms).
Does the sentence above means sometimes it will not work?
@aleju thanks for this great repository! It is generally ok to use anything on github (since it is opensource). However we want to ask you if we use the papers / blogs for academic research. we will happy to credit you and the github as the source. thanks!
Hi, thanks so much for all your great work! AMAZING stuff.
In this paper summary (https://github.com/aleju/papers/blob/master/neural-nets/Progressive_Growing_of_GANs.md) there's this todo:
"(TODO exact formula for c?)"
and I was wondering whether you ever figured that out. This is the last bit of the paper I have trouble understanding.
Hi Alexander Jung,
First of all, a very heartily thanks for this wonderful repository. I have seen that you are very aware of current research and you also have interest in image generation/augmentation. I have gone through
DRAW-2015, LAPGAN-2015, and DCGAN-2016. As the above mentioned works date two year back, I wanted to explore the recent studies in the same.
I have also explored similar problem statement such as super-resolution(SRGAN), and image-to-image translation(pix2pix,cyclegan). It would be really helpful if you can share your knowledge of this domain or similar problems to give me an idea of recent research in the same.
Thanks and Regards,
Ram
In this paper, the author proposed that for mnist dataset, the input layer size is 3636 . For CIFAR100, it is 9494. As we all know that each imageis 28281 in mnist and 32323 in CIFAR10. How can we understand this setting? Do you have some ideas?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.