View source on GitHub |
An append-only trackable mapping data structure with string keys.
tf.contrib.checkpoint.Mapping(
*args, **kwargs
)
Maintains checkpoint dependencies on its contents (which must also be trackable), named based on its keys.
Note that once a key has been added, it may not be deleted or replaced. If
names may not be unique, see tf.contrib.checkpoint.UniqueNameTracker
.
Attributes | |
---|---|
layers
|
|
losses
|
Aggregate losses from any Layer instances.
|
non_trainable_variables
|
|
non_trainable_weights
|
|
trainable
|
|
trainable_variables
|
|
trainable_weights
|
|
updates
|
Aggregate updates from any Layer instances.
|
variables
|
|
weights
|
Methods
get
get(
key, default=None
)
D.get(k[,d]) -> D[k] if k in D, else d. d defaults to None.
items
items()
D.items() -> a set-like object providing a view on D's items
keys
keys()
D.keys() -> a set-like object providing a view on D's keys
update
update(
*args, **kwargs
)
values
values()
D.values() -> an object providing a view on D's values
__contains__
__contains__(
key
)
__eq__
__eq__(
other
)
Return self==value.
__getitem__
__getitem__(
key
)
__iter__
__iter__()
__len__
__len__()