FMRSS Net: Fast Matrix Representation-Based Spectral-Spatial Feature Learning Convolutional Neural Network for Hyperspectral Image Classification

Table 3

---

Parameter Settings for Indian Pines/Salinas

---

INPUT:

(i) Input data: ()

(ii) Learning rate: 1

(iii) Batch size: 100

CONVOLUTION 1:

(i) 6 feature maps

(ii) Kernel size: ()

(iii) Feature map size: ()

(iv) Training parameters number: 156

(v) Activation function: Sigmoid

MAX POOLING:

(i) 6 feature maps

(ii) Kernel size:

(iii) Feature map size: ()

(iv) Training parameters number: 12

(v) Pooling function: Max pooling sampling

CONVOLUTION 2:

(i) 12 feature maps

(ii) Kernel size:

(iii) Feature map size: ()

(iv) Training parameters number: 300

(v) Activation function: Sigmoid

FULL CONNECTION:

(i) Units number:

(ii) Training parameters number: 19300

(iii) Activation function: Softmax

OUTPUT:

(i) Units number , named classes number

(ii) Training parameters number: 1616

---