Skip to main content
Ctrl+K

Vision Architectures (main)

  • API Reference
  • API Reference

Section Navigation

  • Blocks
    • Heads3D
    • MBConv3D
    • Squeeze and Excitation
    • Transformer
    • CNN
  • Image Readers
    • SafeTensorsReader
  • Layers
    • Latent Space
    • Upsample / Downsample
    • Attention
    • Codebook
    • Embeddings
  • Nets
    • DETR3D
    • ViT3D
    • Swin3D
    • CaiT3D
    • UperNet3D
    • SwinV23D
    • FPN2D
    • FPN3D
    • SymSwin3D
    • UNetR3DDecoder
    • UperNet2D
    • Perceiver3D
    • MaxViT3D
  • Schedulers
    • Learning Rate Schedulers
    • Cyclic
    • Noise
    • Sigmoid
  • Transforms
    • CropPad
    • Resize
    • Spatial
    • Clipping
  • Utils
    • Residual Connections
    • Timesteps
    • Normalizations
    • Pipeline Parallelism
    • Clamping / Clipping
    • Activations
    • Rearrange
    • CustomBaseModel
    • Tensor Splitter and Merger
    • ActivationCheckpointing
  • API Reference
  • Blocks

Blocks#

This section documents the blocks components.

  • Heads3D
  • MBConv3D
  • Squeeze and Excitation
  • Transformer
  • CNN

previous

API Reference

next

Heads3D

© Copyright 2023 onwards, Arjun Agarwal.

Created using Sphinx 8.1.3.

Built with the PyData Sphinx Theme 0.16.1.