-
stylegan2-pytorch
Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
In addition to the generator output layer differences already pointed out, there are likely other architectural differences. WGAN-GP has a fairly easy-to-use official codebase. I recommend running your dataset through it and verifying whether your implementation gets similar FIDs to it.
Not quite, SG2 removed progressive growing from SG1 due to "phase artefacts", see Section 4 of the paper. There are a few PyTorch reimplementations [here and here] of SG2 that may be compatible with 30-series. If not, SG1 works pretty great for faces as well, good luck. :)