问在sess.run上更新Tensorflow模型的权重

EN

### in the training phase ####
X_eval, Y_eval, O_eval, W_eval, cost_eval, train_step_eval = sess.run([X, Y, O_out, W, cost, train_step], feed_dict={X:x_batch , Y:y_batch})

### when the training is finished (closed for loop) ###
print(W_eval)
Y_out, W_eval2 = sess.run([O_out, W], feed_dict = {X:labeled_features[:,: - n_labels], Y:labeled_features[:,- n_labels :]})
print(W_eval2)

import tensorflow as tf

a = tf.get_variable('a', initializer=42.)

train_step = a.assign(a + 1)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    value, _ = sess.run([a, train_step])  # will update a
    print(value)
    value = sess.run([a])  # will not update a
    print(value)
    value = sess.run([a])  # will not update a
    print(value)

42.0
[43.0]
[43.0]