MaCow (Unf)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonImageNet 64x64
Bits per dim· 2019-02-12
3.75
best: 4.351 (Logsparse (6 layers))
MaCow: Masked Convolutional Generative Flow arXiv:1902.04208
Image GenerationonCelebA 256x256
bpd· 2019-02-12
0.95
best: 0.51 (Efficient-VDVAE)
MaCow: Masked Convolutional Generative Flow arXiv:1902.04208