1 रिपॉजिटरी
Awesome GitHub RepositoriesDistribution Regularizers
Penalties that encourage embeddings or weights to share a common Lp norm or zero mean to promote uniformity.
Distinct from Embedding Regularization: Distinct from Embedding Regularization: focuses on distribution-level constraints (norm sharing, zero mean) rather than noise injection or general constraints.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Distribution Regularizers. Refine with filters or upvote what's useful.
Awesome Distribution Regularizers GitHub Repositories
AI के साथ बेहतरीन रिपॉजिटरी खोजें।हम AI का उपयोग करके सबसे सटीक रिपॉजिटरी खोजेंगे।
- kevinmusgrave/pytorch-metric-learning
KevinMusgrave/pytorch-metric-learning
6,328GitHub पर देखेंPyTorch Metric Learning is an open-source library for training neural networks to produce similarity-preserving embedding spaces. It provides a modular framework where interchangeable loss functions, mining strategies, and evaluation tools can be composed to learn representations that map similar items to nearby points and dissimilar items to distant points in the embedding space. The library distinguishes itself through a highly configurable architecture that separates concerns across several interchangeable components. Users can assemble custom loss functions from pluggable distance metrics
Ships distribution regularizers that encourage uniform Lp norms or zero-mean embeddings during metric learning training.
Pythoncomputer-visioncontrastive-learningdeep-learning
