1 repo
Awesome GitHub RepositoriesZero-Shot Inference Engines
Logic for performing classification tasks on unseen data without requiring additional training or fine-tuning.
Distinguishing note: Focuses on inference-time similarity calculations for classification, distinct from training-time optimization.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Zero-Shot Inference Engines. Refine with filters or upvote what's useful.
Awesome Zero-Shot Inference Engines GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- openai/CLIP
openai/CLIP
32,614View on GitHubCLIP is a neural network architecture designed to map visual and textual data into a shared latent vector space. By utilizing transformer-based feature extraction and multi-modal tokenization, the system aligns images and natural language strings, enabling cross-modal similarity analysis and semantic classification. The project functions as a zero-shot classification engine, identifying image content by calculating the cosine similarity between visual features and arbitrary text labels without requiring task-specific retraining. Beyond inference, it serves as a research toolkit for evaluating
Determines the most likely label for an input by calculating the cosine similarity between image and text embeddings without retraining.
Jupyter Notebookdeep-learningmachine-learning
