Skip to main content

Table 4 Basic composition of the functional operators in each block that constitute the DenseNet121 Architecture

From: Review of deep learning methods for remote sensing satellite images classification: experimental survey and comparative analysis

Block

Units (n)

Operators (F)

Resolutions (H \(\times\) W)

Channels

Block A

2

Conv, ReLu, MaxPool, BatchNorm

112 \(\times\) 112

64

Block B

112

Conv, ReLu, BatchNorm

56 \(\times\) 56, 28 \(\times\) 28,14 \(\times\) 14, 7 \(\times\) 7

128,32

Block C

1

Conv, ReLu, BatchNorm

56 \(\times\) 56

32

Block D

1

Conv, Relu, MaxPool, BatchNorm, AvgPool

56 \(\times\) 56

128

Block E

2

Conv, AvgPool, BatchNorm, Relu

28 \(\times\) 28

256

Block F

1

Conv, BatchNorm, AdaptiveMaxPool, Linear, Relu, BatchNorm

7 \(\times\) 7

–

Block G

1

Linear, Relu, BatchNorm

7 \(\times\) 7

512