Welcome to VFormer’s documentation!

Contents

• VFormer
• Installation
  • From source (recommended)
  • Stable release

API Reference

• Attention
  • Vanilla Self Attention O(\(n^2\))
  • Cross Attention
  • Spatial Self Attention
  • Window Attention
  • Memory Efficient self Attention O(n)
  • Gated Positional Self Attention
  • Self Attention with Convolutional Projection
• Common
  • Base Classification Model
  • Blocks
• Decoder
  • MLP
  • Perceiver IO Decoder
  • Task Heads
• Encoders
  • Embedding Layers
  • Cross Encoder
  • FeedForward MLP
  • Pyramid Encoder
  • Perceiver IO Encoder
  • Swin Encoder
  • Vanilla Encoder
  • ConViT
  • ConvVT
• Functional
  • Patch Merging
  • Normalization Layers
• Models
  • Classification
  • Dense Prediction
• Utilities
  • Generic Utilities
  • Window Attention Utilities
• Visualisation
  • Rollout
  • Gradient Rollout

Indices and tables

• Index

• Module Index

• Search Page