iamuspace

I worked OK by changing some code. stacked_rnn = [] for i in range(15): stacked_rnn.append(tf.nn.rnn_cell.GRUCell(32)) gru1 = tf.nn.rnn_cell.MultiRNNCell( stacked_rnn ) cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=y_, labels=y))

I found the solution to avoid "AUC : 1.0" in cnn.py change n_sample number . default is 10 I changed to 300 then, AUC is below Epoch : 0 AUC...