Open yasohasakii opened 3 months ago
Hi , I met theloss nan issue too, and I added torch.autograd.set_detect_anomaly(True) then got RuntimeError: Function 'MulBackward0' returned nan values in its 1th output.. The gigagan-python of mine is 0.2.20, how can I fix this issue, please!
loss nan
torch.autograd.set_detect_anomaly(True)
RuntimeError: Function 'MulBackward0' returned nan values in its 1th output.
I have set vision_aided_divergence_loss_weight=0. and still got wrong like below, please help me if you are convenient, thanks!
vision_aided_divergence_loss_weight=0.
Hi , I met the
loss nan
issue too, and I addedtorch.autograd.set_detect_anomaly(True)
then gotRuntimeError: Function 'MulBackward0' returned nan values in its 1th output.
. The gigagan-python of mine is 0.2.20, how can I fix this issue, please!