High level model algorythm descriptions

[Tekniklee]

I've been trying to file some place that has good, high-level descriptions of the various algorythms used by each model. I've seen some generalized information, such as the descriptions in the Training Guide. Those are good, but a bit too broad for me. I've also looked through the Python code, but it's hard to see the forest because of all the trees. Is there a lay-technical resource like this? If not, where or from whom can I get the info and I'll try to grok it and write something up.

[torzdf]

Your best bet is to search for Autoencoders and read up on that.

Then try to apply that with what we do (i.e share the encoder, then swap the decoders on convert)

[Tekniklee]

I'll give that a try. I understand most of the operations involved, but not how the models differ from each other in their high level game plans. Excuse me while I duck down this rabbit hole....

[bryanlyon]

If you really feel that you're familiar enough with Neural Networks then all the models are located in https://github.com/deepfakes/faceswap/t ... rain/model and you can see each of them and their differences pretty easily.

[Tekniklee]

That's kind of what I've been trying to do. However, my programming peak was back in the late 90's with Visual Basic, SQL databases and event driven interfaces. All of the underlying technology - python, tensorflow, keras, programming environments in general are new to me. I wrestled with Anaconda and survived. I'm making progress on all of those area and in other ML areas, but right now I could really use a Cliff Notes version of what the models are attempting to do. Reading through the code is...let's just say it's hard to see the forest for all the trees. I'll see if I can digest th Autocoder search results.