TensorFlow 报错：InvalidArgumentError (see above for traceback): tags and values not the same shape: []

报错源码：

loss = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(labels_holder,1), logits=label_predict)
correct_predict = tf.equal(tf.argmax(label_predict, 1), tf.argmax(labels_holder, 1))
accuracy = tf.reduce_mean(input_tensor=tf.cast(x=correct_predict, dtype=tf.float32))
train_op = tf.train.GradientDescentOptimizer(learning_rate=self.lr).minimize(loss=loss)
tf.summary.scalar(name="loss", tensor=loss)
tf.summary.scalar(name="accuracy", tensor=accuracy)
merged = tf.summary.merge_all()
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init_op)
    writer = tf.summary.FileWriter(logdir="./summary/", graph=sess.graph)
    for i in range(self.epoch_num):
        batch_images, batch_labels = mnist.train.next_batch(self.batch_size)
        batch_images = tf.reshape(tensor=batch_images, shape=[self.batch_size, 28, 28, 1])
        batch_images = tf.image.resize_images(images=batch_images,size=(32,32))
        sess.run(train_op, feed_dict={images_holder:batch_images.eval(), labels_holder:batch_labels})
        accuracy_result = sess.run(accuracy, feed_dict={images_holder: batch_images.eval(), labels_holder: batch_labels})
        summary_result = sess.run(fetches=merged, feed_dict={images_holder: batch_images.eval(), labels_holder: batch_labels})
        writer.add_summary(summary=summary_result, global_step=i)

 

报错信息：

InvalidArgumentError (see above for traceback): tags and values not the same shape: [] != [100] (tag 'loss')
     [[node loss (defined at /Users/jiweiwang/Git Repository/machine_learning_basis/tensorflow_practice/image_recognition/classical_network/LeNet-5/LeNet-5.py:104)  = ScalarSummary[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](loss/tags, SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits)]]

 

这里出错的原因是定义的 loss 采用 sparse_softmax_cross_entropy_with_logits

loss = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(labels_holder,1), logits=label_predict)

查阅 TensorFlow API：https://tensorflow.google.cn/api_docs/python/tf/losses/sparse_softmax_cross_entropy

sparse_softmax_cross_entropy_with_logits 返回：Weighted loss Tensor of the same type as logits. If reduction is NONE, this has the same shape as labels; otherwise, it is scalar.

即返回和输入标签具有相同形状的张量

 

解决方法：

将 tf.summary.scalar(name="loss", tensor=loss) 改为 tf.summary.histogram(name="loss", tensor=loss)