XcyMaster

> Encountered the same problem, > Audios_tf = tf.placeholder(tf.float32, shape=[batch_size, None], name='1_input') > Preds_th, loss_th = sess.run((preds, loss), feed_dict={labels_tf: np.array(y_test), audios_tf: np.array(audios_np)}) > Traceback (most recent call last): > File...

> I solved it. In sess, the normalized place went wrong. > mean, var = tf.nn.moments(m, axes=[2]) leads to tf.nn.batch_normalization(x=m, mean=mean, variance =var, offset=shift, scale=scale, variance_epsilon=0) The data does not...

hi,I just met the same problem with you,but my tensorflow path is corresponds to the path in tf_sampling_compile.sh. Can you help me? thanks a lot. 



Have you sloved it？ I got the same trouble

hey guys ，Have you got it? I want a copy,too. Can you send me? my email [email protected]. Thanks a lot.

请问你解决了这个报错吗？我也遇到了同样的问题

well , bro ,I just met the same problem , have you slove it? py3.6+tf1.14