Skip to main content
EURASIP Journal on Wireless Communications and Networking

Table 2 Comparison of computation complexity

From: A novel deep learning automatic modulation classifier with fusion of multichannel information using GRU

 

Trainable parameters (K)

Inference time (ms)

FGDNN

253

0.265

LSTM-FC

321

0.248

CNN-LSTM2

1117

0.477

CNN-LSTM

397

0.311

LSTM2

196

0.201

GRU2

148

0.183

Back to article page