assign_from_checkpoint_fn( model_path, var_list, ignore_missing_vars=False, reshape_variables=False )
See the guide: Framework (contrib) > Variables
Returns a function that assigns specific variables from a checkpoint.
If ignore_missing_vars is True and no variables are found in the checkpoint it returns None.
model_path: The full path to the model checkpoint. To get latest checkpoint use
model_path = tf.train.latest_checkpoint(checkpoint_dir)
var_list: A list of
Variableobjects or a dictionary mapping names in the checkpoint to the corresponding variables to initialize. If empty or
None, it would return
ignore_missing_vars: Boolean, if True it would ignore variables missing in the checkpoint with a warning instead of failing.
reshape_variables: Boolean, if True it would automatically reshape variables which are of different shape then the ones stored in the checkpoint but which have the same number of elements.
A function that takes a single argument, a
tf.Session, that applies the assignment operation. If no matching variables were found in the checkpoint then
None is returned.
ValueError: If var_list is empty.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.