As a result of upgrading the sensor flow version, the checkpoint file format has been changed.

The output format of the tensorflow learning model has changed from the previous one.
Only model.ckpt was
model.ckpt-1111.data-00000-of-000001,
model.ckpt-1111.index,
model.ckpt-1111.meta
I am having a hard time dealing with it because it has been changed to 3 files.

I would like to know which ckpt file to refer to and an example code.
~~~The following is a part of the code I am using~~~

images_placeholder=tf.placeholder("float", shape=(None,IMG_PIXELS))
keep_prob=tf.placeholder("float")
logs = reference(images_placeholder, keep_prob)
sess=tf.InteractiveSession()
saver=tf.train.Saver()
sess.run(tf.global_variables_initializer())
saver.restore(sess, "model.ckpt")

python tensorflow

2022-09-30 19:10

1 Answers

The checkpoint file format has been changed since tensorflow r12.

If you want to save in the past format,

import tensorflow as tf
from tensorflow.core.protobuf import saver_pb2
...
saver=tf.train.Saver (write_version=saver_pb2.SaverDef.V1)
saver.save(sess, './model.ckpt', global_step=step)

(cf:https://stackoverflow.com/questions/41048819/how-to-restore-a-model-by-filename-in-tensorflow-r12)

For restore,

with tf.Session() asess:
    saver=tf.train.import_meta_graph('/tmp/model.ckpt.meta')
    saver.restore(sess, "/tmp/model.ckpt")

cf:https://stackoverflow.com/questions/41265035/tensorflow-why-there-are-3-files-after-saving-the-model

2022-09-30 19:10

If you have any answers or tips

Popular Tags

python x 4647

android x 1593

java x 1494

javascript x 1427

c x 927

c++ x 878

ruby-on-rails x 696

php x 692

python3 x 685

html x 656