You must feed a value for placeholder tensor ‘XXXXXXX’ with dtype float
你是否也在想用tensorboard时因出现这个错误而苦恼呢?
马上检查你的merge_all在run的时候有没有feed数据!!!!
别问为什么!网上其他帖子都是坑!!!
类似这样就行:
summary_op = tf.summary.merge_all() sess = tf.Session() train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph) saver = tf.train.Saver()
summary_str = sess.run(summary_op,feed_dict={x:train_batch,y_:train_label_batch}) train_writer.add_summary(summary_str, step)