# Create some variables.
v1 = tf.get_variable("v1", shape=[3], initializer = tf.zeros_initializer)
v2 = tf.get_variable("v2", shape=[5], initializer = tf.zeros_initializer)
inc_v1 = v1.assign(v1+1)
dec_v2 = v2.assign(v2-1)
# Add an op to initialize the variables.
init_op = tf.global_variables_initializer()
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, initialize the variables, do some work, and save the
# variables to disk.
with tf.Session() as sess:
sess.run(init_op)
# Do some work with the model.
inc_v1.op.run()
dec_v2.op.run()
# Save the variables to disk.
save_path = saver.save(sess, "/tmp/model.ckpt")
print("Model saved in path: %s" % save_path)
Restore variables
The tf.train.Saver object not only saves variables to checkpoint files, it also restores variables. Note that when you restore variables you do not have to initialize them beforehand. For example, the following snippet demonstrates how to call the tf.train.Saver.restore method to restore variables from the checkpoint files:
tf.reset_default_graph()
# Create some variables.
v1 = tf.get_variable("v1", shape=[3])
v2 = tf.get_variable("v2", shape=[5])
# Add ops to save and restore all the variables.
saver = tf.train.Saver()
# Later, launch the model, use the saver to restore variables from disk, and
# do some work with the model.
with tf.Session() as sess:
# Restore variables from disk.
saver.restore(sess, "/tmp/model.ckpt")
print("Model restored.")
# Check the values of the variables
print("v1 : %s" % v1.eval())
print("v2 : %s" % v2.eval())
Note: There is not a physical file called /tmp/model.ckpt. It is the prefix of filenames created for the checkpoint. Users only interact with the prefix instead of physical checkpoint files.
Choose variables to save and restore
If you do not pass any arguments to tf.train.Saver(), the saver handles all variables in the graph. Each variable is saved under the name that was passed when the variable was created.
It is sometimes useful to explicitly specify names for variables in the checkpoint files. For example, you may have trained a model with a variable named "weights" whose value you want to restore into a variable named "params".
It is also sometimes useful to only save or restore a subset of the variables used by a model. For example, you may have trained a neural net with five layers, and you now want to train a new model with six layers that reuses the existing weights of the five trained layers. You can use the saver to restore the weights of just the first five layers.
You can easily specify the names and variables to save or load by passing to the tf.train.Saver() constructor either of the following:
A list of variables (which will be stored under their own names).
A Python dictionary in which keys are the names to use and the values are the variables to manage.
Continuing from the save/restore examples shown earlier:
tf.reset_default_graph()
# Create some variables.
v1 = tf.get_variable("v1", [3], initializer = tf.zeros_initializer)
v2 = tf.get_variable("v2", [5], initializer = tf.zeros_initializer)
# Add ops to save and restore only `v2` using the name "v2"
saver = tf.train.Saver({"v2": v2})
# Use the saver object normally after that.
with tf.Session() as sess:
# Initialize v1 since the saver will not.
v1.initializer.run()
saver.restore(sess, "/tmp/model.ckpt")
print("v1 : %s" % v1.eval())
print("v2 : %s" % v2.eval())
方法2：
checkpoint_file = tf.train.latest_checkpoint(FLAGS.checkpoint_dir)
graph = tf.Graph()
with graph.as_default():
session_conf = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement)
sess = tf.Session(config=session_conf)
with sess.as_default():
# Load the saved meta graph and restore variables
saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file))
saver.restore(sess, checkpoint_file)
# Get the placeholders from the graph by name
w = graph.get_operation_by_name("word_embedding/W").outputs[0]
print sess.run(w)
模型中 关于W的定义：
self.W = tf.Variable(10.0, name = "W")