MCPcopy Create free account
hub / github.com/VincentHancoder/SSGD / MixFFN

Class MixFFN

mmdet/models/backbones/pvt.py:23–99  ·  view source on GitHub ↗

An implementation of MixFFN of PVT. The differences between MixFFN & FFN: 1. Use 1X1 Conv to replace Linear layer. 2. Introduce 3X3 Depth-wise Conv to encode positional information. Args: embed_dims (int): The feature dimension. Same as `MultiheadAttenti

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

__init__Method · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected