什么珂的博客

参考：https://blog.youkuaiyun.com/qq_25109263/article/details/77827255训练完模型后，先定义一个saver：saver = tf.train.Saver()保存模型：with tf.Session() as sess: sess.run(tf.global_variables_initializer()) for...

1. 将想要命名的值添加代码及缩进with tf.name_scope('input'): with tf.name_scope('train_data'): ph_train_data = tf.placeholder(tf.float32, [None, n_time_step, n_dim]) with tf.name_scope('train_labe...