Table 3.
A table summary of MiniVGGNet architectures for 32 × 32 × 3 input image. To build MiniVGGNet2 and MiniVGGNet3, one layer or two layers were added to the MiniVGGNet architecture, respectively

Layer Type	Output Size	Filter Size/Stride
INPUT IMAGE	32 × 32 × 3
CONV	32 × 32 × 32	3 × 3 × 32
ACT	32 × 32 × 32
BN	32 × 32 × 32
CONV	32 × 32 × 32	3 × 3 × 32
ACT	32 × 32 × 32
BN	32 × 32 × 32
POOL	16 × 16 × 32	2 × 2
DROPOUT	16 × 16 × 32
CONV	16 × 16 × 64	3 × 3 × 64
ACT	16 × 16 × 64
BN	16 × 16 × 64
CONV	16 × 16 × 64	3 × 3 × 64
ACT	16 × 16 × 64
BN	16 × 16 × 64
POOL	8 × 8 × 64	2 × 2
DROPOUT	8 × 8 × 64
FC	512
ACT	512
BN	512
DROPOUT	512
FC	5
SOFTMAX	5