disentangling-disentanglement
disentangling-disentanglement copied to clipboard
run error about independance.sh
When I run
python3 main.py --name dsprites_beta_1_pz_norm_iso --model dsprites --skip-test --epochs 20 --lr 5e-4 --batch-size 64 --latent-dim 10 --beta 1. --prior-variance iso
an error occurred
ValueError: Expected parameter probs (Tensor of shape (1, 64, 1, 64, 64)) of distribution LogitRelaxedBernoulli(probs: torch.Size([1, 64, 1, 64, 64])) to satisfy the constraint Interval(lower_bound=0.0, upper_bound=1.0), but found invalid values
Can you help me figure out this problem? Thank you very much!