Skip to main content

Official Journal of the Asia Oceania Geosciences Society (AOGS)

Table 6 The architecture of LSNet

From: Evaluation of different machine learning models and novel deep learning-based algorithm for landslide susceptibility mapping

Layer

Feature map

Feature map

Size

Kernel Size

Stride

Activate

Input

  

224 × 224 × 3

  

ReLU

1

2 × CNN

64

224 × 224 × 64

3 × 3

1

ReLU

Max pooling

64

112 × 112 × 64

3 × 3

2

ReLU

2

2 × CNN

128

112 × 112 × 128

3 × 3

1

ReLU

Max pooling

128

56 × 56 × 128

3 × 3

2

ReLU

3

2 × CNN

256

56 × 56 × 256

3 × 3

1

ReLU

Max pooling

256

28 × 28 × 256

3 × 3

2

ReLU

4

2 × CNN

512

28 × 28 × 512

3 × 3

1

ReLU

Max pooling

512

14 × 14 × 512

3 × 3

2

ReLU

5

2 × CNN

512

14 × 14 × 512

3 × 3

1

ReLU

Max pooling

512

7 × 7 × 512

3 × 3

2

ReLU

6

FC

–

25,088

–

–

ReLU

7

FC

–

1024

–

–

ReLU

8

FC

–

256

–

–

ReLU

9

FC

–

128

–

–

SoftMax