Skip to main content

Table 1 Architecture of the SR-ConvLSTM

From: A deep learning-aided temporal spectral ChannelNet for IEEE 802.11p-based channel estimation in vehicular communications

Layer

Type

Number of filters

Size of filters

Activation function

1

ConvLSTM(Input)

64

9 ×9

ReLU

2

BN

–

–

–

3

ConvLSTM

32

1 ×1

ReLU

4

BN

–

–

–

5

ConvLSTM(Output)

1

5 ×5×5

ReLU