Likelihood-Regret Official implementation of Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder at NeurIPS 2020. Training To train the VAEs, use appropriate arguments and run this command: python train_pixel.py Evaluation To evaluate likelihood regret’s OOD detection performance, run python compute_LR.py To evaluate likelihood ratio, run python test_likelihood_ratio.py To evaluate input complexity, run python test_inputcomplexity.py Above commands will save the numpy arrays containing the OOD scores for in-distribution and OOD samples in specific location, and to compute aucroc score, run […]

A software manager for easy development and distribution of Python code. The main features that Piper adds to Python are: Support for large-scale, multi-package projects Reproducibility (clear, transparent dependency management) Robust development-lifecycle, from blueprinting to distribution Piper is inspired by what Maven is for Java and uses Pip and Virtual Environments. Why Piper Python is great in many things, particularly for scripting. But it is powerful enough to create complex software too. Still, when doing so, it lacks some robustness […]