Skip to main content

Table 5 Performance of Resnet-LSTM model before and after introducing attention mechanism

From: A CNN-LSTM-att hybrid model for classification and evaluation of growth status under drought and heat stress in chinese fir (Cunninghamia lanceolata)

Stress

Model

Acc (%)

Pr(%)

Re(%)

F1-score (%)

Heat

Resnet50-LSTM

92.18

92.14

92.06

92.10

Resnet50-LSTM-att

96.91

96.81

96.79

96.80

Drought

Resnet50-LSTM

91.52

91.52

91.37

91.44

Resnet50-LSTM-att

96.05

95.92

95.88

95.90