Enrico Ros

The site seems down again. This is a very useful tool - are there ways to keep the project running, or are there alternative products we can use?

Impressive! It's not fully reproducible yet but pictures converge to similar styles! Like, with seed=1234 I get all pictures made of Leaves :D

I've tried adding `np.random.seed(seed)`, and prefer without it. Then tried `torch.set_deterministic(True)` and gotten this explanation at runtime: `RuntimeError: upsample_bilinear2d_backward_cuda does not have a deterministic implementation, but you set 'torch.set_deterministic(True)'. You...

Removed line by line to get to the minimum set that is deterministic (md5sum of the png files are identical). Minimal code: ` if exists(seed): torch.set_deterministic(True) torch.manual_seed(seed) ` Submitting patch!...

Opened on pull request https://github.com/lucidrains/big-sleep/pull/12. I hope it's pixel-equal on other versions of PyTorch/CUDA/OSs.

Note after further testing: this will work well on a single execution, but there's a strange issue remaining when looping code such as the following: ``` while True: imagine =...

_Update for the looping case_. If after forward() finishes, we delete the model (before its recreation in a new `Imagine()`), the results become more predictable, but there's still some dangling...

@htoyryla What kind of difference do you see? I love the results here, some are really outstanding

@htoyryla can you try with `torch.set_deterministic(True)` and see if you get reproducible results? Run that line as early as possible. Then it could depend on the status of memory/CUDA initialization......

@htoyryla Are the results also the same as the original notebook or different?