Table 15 The optimal architecture searched for the fashion and MRDBI dataset.

From: Fractal and chaotic map-enhanced grey wolf optimization for robust fire detection in deep convolutional neural networks

Type

Set up

Filter size

Stride size

Feature maps

Kernel size

Stride size

Type

Neurons

Convolution

2

1

26

    

Convolution

6

3

68

    

Convolution

8

4

96

    

Convolution

6

3

68

    

Pooling

   

4

4

Average

 

Convolution

4

2

48

    

Fully-connected

    

1428

Fully-connected

    

10

Back to article page