Skip to main content
. 2021 Dec 11;21(24):8291. doi: 10.3390/s21248291

Table 4.

Detailed summary of the spatial-temporal model for abnormal activity recognition.

Layer (Type) Output Shape Numbers of Parameters
InputLayer (None, 30, 1000) 0
LSTM (None, 30, 256) 1,287,168
LSTM (None, 30, 128) 197,120
Batch Normalisation (None, 30, 128) 512
LSTM (None, 30, 64) 49,408
Flatten (None, 1920) 0
Batch Normalisation (None, 1920) 7680
Dense (None, 256) 491,776
Dropout (None, 256) 0
Dense (None, 128) 32,896
Dropout (None, 128) 0
Dense (None, 2) 258