def __init__(self, batch_size, x_dimension, dnn_width, cnn_filterSize, cnn_filterSize2, cnn_filterNum, cnn_filterNum2 , learning_rate, dropoutRate, choice, max_plot_len, max_len, parameterPath):

Fig.1 Overall on QACNN model

Fig.1 shows the QACNN model. The QACNN model is implemented by __init__ function. The __init__ function include 4 parts: # initialize parameters #, # CNN1 #, # CNN2 #, and # compute #.

Fig.2 The flowchart of function __init__()

Fig.2 shows the flowchart of function __init__().

#initialize parameters# 也就是 Similarity Mapping Layer, including embedding layer and compare layer.

#CNN1# 建立CNN1模型，也就是 QACNN Layer 中的 first stage CNN。

#CNN2# 建立CNN2模型，也就是 QACNN Layer 中的 second stage CNN。

#compute# 是 Prediction Layer。#compute# part predict the choice, compute the loss value, and train the model by using AdamOptimizer, then save the model status after training

results matching ""

    No results matching ""