1 个仓库
Awesome GitHub RepositoriesStatistical Parameter Caching
Persisting computed distribution parameters to disk to avoid redundant neural network passes.
Distinct from Disk-Based Offloading Systems: Distinct from Disk-Based Offloading Systems: focuses on caching pre-computed statistical parameters for evaluation, not intermediate query results.
Explore 1 awesome GitHub repository matching data & databases · Statistical Parameter Caching. Refine with filters or upvote what's useful.
Awesome Statistical Parameter Caching GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- mseitzer/pytorch-fid
mseitzer/pytorch-fid
3,849在 GitHub 上查看pytorch-fid is a PyTorch-based evaluator and image distribution analysis library used to calculate the Fréchet Inception Distance. It functions as a benchmarking tool that maps image pixels to high-dimensional feature vectors using a pre-trained convolutional neural network to measure the mathematical divergence between real and synthetic datasets. The library quantifies the quality and diversity of generative models by representing image feature sets as mean and covariance matrices. It allows for the extraction of latent representations from specific neural network layers, with configurable
Persists computed distribution parameters to disk to eliminate redundant neural network passes across multiple evaluations.
Pythondeep-learningfidfid-score
