1 مستودع
Efficient vision transformer architectures utilizing convolutional embedding and staged downsampling.
Distinct from Vision Transformers: Distinct from general Vision Transformers: specifically refers to the LeViT architecture variant.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · LeViT Architectures. Refine with filters or upvote what's useful.
This library provides a comprehensive collection of modular building blocks and research-backed architectures for implementing vision transformers within the PyTorch framework. It serves as a centralized repository for constructing, training, and analyzing attention-based models, offering a wide array of specialized variants designed for image classification and visual representation learning. The project distinguishes itself through a focus on architectural efficiency and flexibility, supporting diverse input formats including non-square images and volumetric data like video. It incorporates
Uses convolutional embedding and staged downsampling to provide an efficient architecture for image classification tasks.