Tensorflow 特定分支机构的汇总表

我有一个tensorflow图，它有一个用于训练的复杂损失函数，但用于评估的更简单（它们共享祖先）。本质上

train_op = ... (needs more things in feed_dict etc.)
acc = .... (just needs one value for placeholer)

为了更好地理解发生了什么，我添加了摘要。但是打电话

merged = tf.summary.merge_all()

然后

(summ, acc) = session.run([merged, acc_eval], feed_dict={..})

---

tensorflow抱怨占位符的值丢失。

据我所知，要总结特定的tensorflow操作，您应该专门运行它

例如：

# define accuracy ops
correct_prediction = tf.equal(tf.argmax(Y, axis=1), tf.argmax(Y_labels, axis=1))  
accuracy = tf.reduce_mean(tf.cast(correct_prediction, dtype=tf.float32))  

# summary_accuracy is the Summary protocol buffer you need to run, 
# instead of merge_all(), if you want to summary specific ops
summary_accuracy = tf.summary.scalar('testing_accuracy', accuracy) 

# define writer file
sess.run(tf.global_variables_initializer())
test_writer = tf.summary.FileWriter('log/test', sess.graph)

(summ, acc) = sess.run([summary_accuracy, accuracy], feed_dict={..})
test_writer.add_summary(summ)

此外，您还可以使用

tf.summary.merge（）

，。
希望这有帮助