2024-Q1-AI-M 17. DCGAN, WGAN
17.1. Materials / Video (29 May 2024, 18:00)
Video: https://youtube.com/live/84eI97UjrDI?feature=share
Jamboard:
https://jamboard.google.com/d/1eJg1x_MxhO9-hGOSiuG_7148DMYkfRISdTGfCoHP22c/edit?usp=sharing
Materiāli:
https://arxiv.org/pdf/1406.2661.pdf
https://arxiv.org/pdf/1511.06434.pdf5.2
Stream key: 13fp-je0a-r9tc-t4mt-bev1
Tiesības iedotas arī jamboard
Kods no iepriekšējiem gadiem: https://share.yellowrobot.xyz/quick/2024-5-28-3965B5B9-F3E9-40A6-8A73-953EE61402BA.zip
Iepriekšējā gada Video:
https://youtube.com/live/rD1R-GkrCxk?feature=share
Jamboard: https://jamboard.google.com/d/1Ezi_pHjb32uevH5AtQtq65-q74CXWN-9Vz2mtfEBB4g/edit?usp=sharing
Iepriekšējā gada Video: https://youtu.be/ftnIzUdNPYY
Jamboard: https://jamboard.google.com/d/1uaMTfdUbKSjxgn75jxEXEUH1pNhfdBrU5q6mRQOTcMo/edit?usp=sharing
17.2. Implementēt DCGAN
Implementēt DCGAN balstoties uz video instrukcijām
Sagatave: http://share.yellowrobot.xyz/quick/2023-5-18-EB1F688E-2225-47FD-BE8F-7FDE6255AAC4.zip
Algoritms:
http://share.yellowrobot.xyz/upic/0e9419a67428a54774d49b79d44eddfb_1684404148.jpg
Iesniegt ekrānšāviņus ar labākajiem rezultātiem un programmas pirmkodu.
17.3 Implementēt WGAN
Implementēt WGAN balstoties uz video instrukcijām, izmantot iepriekšējo sagatavi
Implement WGAN based on video from 5.1. Use previous template.
Iesniegt ekrānšāviņus ar labākajiem rezultātiem un programmas pirmkodu.
Algoritms:
http://share.yellowrobot.xyz/upic/13494b9d3aeb36b94173028ce135cecf_1684404237.jpg
17.4. Implementēt W-GAN ar uzlabojumiem
Implementēt, izmantojot LFW datu kopu seju ģenerēšanai: https://scikit-learn.org/stable/modules/generated/sklearn.datasets.fetch_lfw_people.html
Implementēt GAN hacks (Izvēlēties un pierakstīt pirmkoda komentāros 2 hacks): https://github.com/soumith/ganhacks#authors https://developers.google.com/machine-learning/gan/problems For example: 2.1. Implement soft labels 2.2. Implement Batches in separate passes of optimizer.step for x_real and x_fake
Iesniegt ekrānšāviņus ar labākajiem rezultātiem un programmas pirmkodu.
https://datascience.stackexchange.com/questions/32671/gan-vs-dcgan-difference
GAN hacks https://github.com/soumith/ganhacks#authors
Gan - the more params the better
Discriminator - too many params, loss 0 killed, too little params loss large do not work
Changing learning rates etc. not good idea
Might help, but not needed:
Discriminator warmup
Discriminator history
Demonstrate mode collapse
Estimate quality by embeddings - deep metric, inception score etc
GAN common problems: https://developers.google.com/machine-learning/gan/problems
#
GAN hacks https://github.com/soumith/ganhacks#authors
Gan - the more params the better
Discriminator - too many params, loss 0 killed, too little params loss large do not work
Changing learning rates etc. not good idea
Might help, but not needed:
Discriminator warmup
Discriminator history
Demonstrate mode collapse
Estimate quality by embeddings - deep metric, inception score etc
GAN common problems: https://developers.google.com/machine-learning/gan/problems
