Tensorflow 模型的保存和读取

Tensorflow 模型的保存和读取

Tensorflow 模型的保存

import tensorflow as tf
tf.compat.v1.disable_eager_execution()

v1 = tf.Variable(tf.random.normal([1,2]), name="v1")
v2 = tf.Variable(tf.random.normal([2,3]), name="v2")

init_op = tf.compat.v1.global_variables_initializer()
saver = tf.compat.v1.train.Saver()

with tf.compat.v1.Session() as sess:
    sess.run(init_op)
    print ("V1:",sess.run(v1))  
    print ("V2:",sess.run(v2))
    saver_path = saver.save(sess, "save/model.ckpt")
    print ("Model saved in file: ", saver_path) 

WARNING:tensorflow:From d:\progra~2\python\virtua~1\py37_x64\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1635: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
V1: [[ 0.81411636 -0.38293725]]
V2: [[ 2.5807521  -0.19250003 -1.373848  ]
 [-0.37121674 -0.5161457  -0.68727684]]
Model saved in file:  save/model.ckpt

Tensorflow 模型的读取

NotFoundError: Restoring from checkpoint failed. This is most likely due to a Variable name or other graph key that is missing from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

NotFoundError: Key v1_1 not found in checkpoint [[node save_1/RestoreV2 (defined at :7) ]]

• 不要重复运行
• 保存与读取分开运行

import tensorflow as tf
tf.compat.v1.disable_eager_execution()

v1 = tf.Variable(tf.random.normal([1,2]), name="v1")
v2 = tf.Variable(tf.random.normal([2,3]), name="v2")

saver = tf.compat.v1.train.Saver()

with tf.compat.v1.Session() as sess:
    saver.restore(sess, "save/model.ckpt")
    print ("V1:",sess.run(v1))  
    print ("V2:",sess.run(v2))
    print ("Model restored")

WARNING:tensorflow:From d:\progra~2\python\virtua~1\py37_x64\lib\site-packages\tensorflow_core\python\ops\resource_variable_ops.py:1635: calling BaseResourceVariable.__init__ (from tensorflow.python.ops.resource_variable_ops) with constraint is deprecated and will be removed in a future version.
Instructions for updating:
If using Keras pass *_constraint arguments to layers.
INFO:tensorflow:Restoring parameters from save/model.ckpt
V1: [[ 0.81411636 -0.38293725]]
V2: [[ 2.5807521  -0.19250003 -1.373848  ]
 [-0.37121674 -0.5161457  -0.68727684]]
Model restored