Pixel CNN ++

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

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

Methodology1 result

Density EstimationonCIFAR-10
NLL (bits/dim)· 2017-01-19
2.92
best: 2.42 (i-DODE)
SOTA
PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications arXiv:1701.05517