> ML_ALGORITHM // NORMALIZING-FLOWS-REALNVP_v1.0
Normalizing Flows (RealNVP)
Generative model class providing exact likelihood evaluation and efficient two-way sampling via invertible neural networks with triangular Jacobians.
Exact Likelihood Generative Modelsdeep-generativehigh-intrinsiclarge (>100k)
Back to All AlgorithmsComputational Complexity
Training Complexity:O(epochs * batch_size * layers * forward)
Inference Complexity:O(layers * inverse_forward)
Hardware Profile
CPU Friendly:No
Requires GPU:Yes
Memory Footprint:high
Interpretability & Data
Interpretability Tier:high-intrinsic
Training Data Needs:large (>100k)
Interpretability Assessment
Computes mathematically exact log-likelihoods without variational lower bounds or approximations.
Suitable Tasks & Supported Modalities
Suitable Tasks:
exact density estimationimage generationanomaly detection
Supported Modalities:
imagetabular
Implementing Libraries
PyTorchLinux Foundation / PyTorch Foundation · v2.4.1
View Speckerashub
Foundational Literature
Common Pitfalls & Warnings
- Assigning counter-intuitively high likelihood to out-of-distribution images (e.g., SVHN model assigning higher likelihood to CIFAR) due to low-level texture dominance