大家都知道，在載入模型及對應的權重進行訓練的時候，我們可以整個使用所提供的模型，但是有時候呢？所提供的模型不能很好的滿足我們的要求，有時候我們只需要模型的前幾層然後進行對應的權重賦值，這時候，我們應該怎麼辦呢？tensorflow為我們提供了兩種方法（探索了好久才找到解決辦法，不過感覺蠻有用的，分享給大家啦！）：

1）在載入模型的時候，使用final_endpoint引數，指定模型階段點：

import tensorflow.contrib.slim.nets as nets
#from tensorflow.contrib.slim.nets.inception import inception_v3, inception_v3_arg_scope
 

import numpy as np
import os

height = 299
width = 299
channels = 3
num_classes=1001

X = tf.placeholder(tf.float32, shape=[None, height, width, channels])
y = tf.placeholder(tf.float32,shape=[None,182])
with slim.arg_scope(nets.inception.inception_v3_arg_scope()):
    logits, end_points = nets.inception
 
.inception_v3_base(X,final_endpoint = "Mixed_7a")
    variables_to_restore=slim.get_variables_to_restore()

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    saver=tf.train.Saver(variables_to_restore)
    saver.restore(sess,os.path.join("E:\\","inception_v3.ckpt"))
    print("Done"
 
)

2）在恢復模型的時候，部分層不使用ckpt檔案中提供的引數：

#-*-coding=utf-8-*-
import tensorflow as tf
import tensorflow.contrib.slim as slim
import tensorflow.contrib.slim.nets as nets
#from tensorflow.contrib.slim.nets.inception import inception_v3, inception_v3_arg_scope
import numpy as np
import os

height = 299
width = 299
channels = 3
num_classes=1001

X = tf.placeholder(tf.float32, shape=[None, height, width, channels])
y = tf.placeholder(tf.float32,shape=[None,182])
with slim.arg_scope(nets.inception.inception_v3_arg_scope()):
    logits, end_points = nets.inception.inception_v3(X, num_classes=num_classes,is_training=False)
with tf.Session() as sess:
    exclude=['Mixed_7c','Mixed_7b','AuxLogits','AuxLogits','Logits','Predictions']
    variables_to_restore=slim.get_variables_to_restore(exclude=exclude)
    sess.run(tf.global_variables_initializer())
    saver=tf.train.Saver(variables_to_restore)
    saver.restore(sess,os.path.join("E:\\","inception_v3.ckpt"))
    print("Done")