1 repo
Awesome GitHub RepositoriesModular Backbone Architectures
Neural network structures designed as decoupled feature extractors for multi-scale output.
Distinguishing note: Focuses on the modularity of feature extractors for downstream tasks rather than specific model architectures.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Modular Backbone Architectures. Refine with filters or upvote what's useful.
Awesome Modular Backbone Architectures GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- huggingface/pytorch-image-models
huggingface/pytorch-image-models
36,386View on GitHubThis project is a comprehensive library of state-of-the-art neural network architectures designed for image classification and feature extraction. It provides a complete deep learning training framework that supports distributed execution, allowing users to build, train, and fine-tune vision models using optimized schedulers and pre-configured training recipes. The library distinguishes itself through a modular backbone architecture that treats neural networks as decoupled feature extractors, enabling the retrieval of multi-scale outputs for downstream tasks like object detection and segmenta
"Neural networks are structured as decoupled feature extractors that provide multi-scale outputs for integration into various downstream computer vision tasks."
Pythonaugmixconvnextdistributed-training
