Mario Klingemann

> On a smart contract level it is always possible, if someone were to write a contract for it, to spawn a "sale-contract" that limits sale to 1 per wallet,...

> If the rule is only enforced in the UI, there is always a risk that someone circumvents it by making a manual request from the browser console/PostMan/curl. Important UI...

I like the idea of having "control tokens". This would be in the spirit that all data on hic et nunc is on-chain and not in some separate database. Maybe...

I am seeing the same error with stylegan2-ada TF checkpoints. Looks like those checkpoints are version "5" - unfortunately just adding "5" to the assert does not help, since further...

Okay - turns out that it works with stylegan2-ada checkpoints, my problem was that my --repo argument was pointing to the old stylegan2 repo.

Thanks for sharing your code! I tried to replicate it, but for some reason I am only getting noise and it seems like reason is the residual tensor is just...

I found the cause of my problem - looks like I am using a newer version of PyTorch in which masked_fill_ does not work with uint8 tensors anymore. The fix...

Ah, good to know. And the total length of tokens is the length of the tensor after the cleaning and transformation: trainset.get_text(text)?

After calculating test sentences for all the speakers it seems like the approximation factor is closer to 6, though I am not sure how sigma and temperature factor further into...

Ah okay - I guess I have to run my estimator again for different sigmas, to see how it affects the factors. Anyway, here is my preliminary lookup table, maybe...