Agricultural Machinery Virtual Assembly System Using Dynamic Gesture Recognitive Interaction Based on a CNN and LSTM Network

Table 5

CNN-LSTM network structure parameters.

CNN-LSTM configuration
6 weight layers
Input (1000 5 20  9 TimeSeries)
Conv1D-128 (7)
Conv1D-128 (7)
MaxPool1D (2)
Flatten
LSTM (100)
FC-100
Softmax (10)
Parameter	Value
Maximum epochs	100
Batch_size	32
Optimiser	Adam
Metrics	Acc & loss
Min–max normalisation	Yes
The number of parameters	380K
Method	Epochs = 5, mean/std