Module repvgg

Module repvgg 

Source
Expand description

RepVGG inference implementation

Key characteristics:

  • Efficient inference architecture through structural reparameterization
  • Single 3x3 conv layer after fusing 3x3 branch, 1x1 branch and identity branch
  • Different configurations including a0-a2, b0-b3 and variants with group convolutions
  • High accuracy with VGG-like plain architecture and training

References:

Structs§

Config

Functions§

repvgg
repvgg_no_final_layer