I'm using the GeomLoss library and trying to use a Sinkhorn loss with the online backend. For a high dimensional (>=512 I think) tensor it gives me an error when compiling the backward code. Here's the repro with GeomLoss:
from geomloss import SamplesLoss
loss = SamplesLoss(loss="sinkhorn", p=2, blur=.05, backend="online")
x = torch.randn(1000, 512, requires_grad=True)
y = torch.randn(1000, 512)
loss(x, y).backward()
I also have this direct repro by copying values from the debugger:
I'm using the GeomLoss library and trying to use a Sinkhorn loss with the online backend. For a high dimensional (>=512 I think) tensor it gives me an error when compiling the backward code. Here's the repro with GeomLoss:
I also have this direct repro by copying values from the debugger:
Both give:
Versions