cnn_lstm_for_text_classify icon indicating copy to clipboard operation
cnn_lstm_for_text_classify copied to clipboard

报错了

Open lhy2749 opened this issue 6 years ago • 3 comments

TypeError:batch_normalization() missing 5 required positional arguments: 'mean', 'variance', 'offset', 'scale', and 'variance_epsilon'

self.outputs, self.final_state = tf.nn.dynamic_rnn(lstm_cell, embedded, dtype=tf.float32, time_major=False) self.out = tf.unstack(tf.nn.batch_normalization(self.outputs), axis=1)[-1] 是因为现在的tensorflow方法修改了么···

lhy2749 avatar May 03 '19 05:05 lhy2749

@lhy2749 我也有相同的错误,请问你解决了吗

vicdu avatar May 11 '19 09:05 vicdu

@lhy2749 我也有相同的错误,请问你解决了吗

把均值方差自己设一下就好了

xuefeng199507 avatar Sep 06 '19 06:09 xuefeng199507

两天之内代码会重新更新和修改,tensorflow很多api更改了,最近考虑更改一下

CementMaker avatar Sep 07 '19 12:09 CementMaker