Computer vision and multimodal learning · MLD-0304
Depthwise separable convolution
A depthwise spatial convolution followed by pointwise channel mixing.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Build efficient image models for phones.
Original caveat
It constrains the operation compared with a full convolution.
Context and aliases
Level: Intermediate. Stages: Architecture · Training · Inference.
Tags: DL · Vision · Multimodal.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Learning Transferable Visual Models From Natural Language Supervision ↗ · Consulted
- Deep Learning: online textbook ↗ · Consulted
- PyTorch neural-network layers ↗ · Reference link
- Original reference URL ↗