Skip to main content

Table 1 The main structures and parameters of DeepACLSTM

From: DeepACLSTM: deep asymmetric convolutional long short-term memory neural models for protein secondary structure prediction

Layer Type Size NP
embedding 21 441
Convolution1D 1 × 42 1806
Convolution2D 3 × 1 168
Dropout1 0.5 0
FC 1 400 706,000
\({LSTM}_f^1\) 300 841,200
\({LSTM}_b^1\) 300 841,200
\({LSTM}_f^2\) 300 721,200
\({LSTM}_b^2\) 300 721,200
Dropout2 0.4 0
FC 2 600 600,600
Softmax 8 4808