為了練習，我想在 tensorflow 中實現一個模型，它可以返回輸入的平方。我的代碼工作正常，但是當我查看 TensorBoard 中的計算圖時，LOSS 操作沒有連接到 Gradients 子圖，也沒有連接到 Adam。為什么是這樣？據我了解，計算梯度，張量流必須推導損失。這是我的代碼：import numpy as npimport tensorflow as tfnp_inp = np.array([3, 6, 4, 2, 9, 11, 0.48, 22, -2.3, -0.48])np_outp = np.power(np_inp, 2)inputs = tf.Variable(np_inp, name='input', trainable=False)outputs = tf.Variable(np_outp, name='output', trainable=False)multiplier = tf.Variable(0.1,                                                       dtype=tf.float64, trainable=True, name='multiplier')mul = inputs * multiplierpredict = tf.square(mul, name='prediction')loss = tf.math.reduce_sum(tf.math.square(predict-outputs), name='LOSS')optimizer = tf.train.AdamOptimizer(0.1)to_minimize = optimizer.minimize(loss)sess = tf.Session()sess.run(tf.global_variables_initializer())logs_path = "./logs/unt"  # path to the folder that we want to save the logs for Tensorboardtrain_writer = tf.summary.FileWriter(logs_path, sess.graph)for i in range(100):  sess.run(to_minimize)print(sess.run({'mult':multiplier}))張量板： https ://gofile.io/?c=jxbWiG