variable

tflearn.variables.variable (args, *kwargs)

Instantiate a new variable.

name: str. A name for this variable.
shape: list of int. The variable shape (optional).
dtype: type. The variable data type.
initializer: str or Tensor. The variable initialization. (See tflearn.initializations for references).
regularizer: str or Tensor. The variable regularizer. (See tflearn.losses for references).
trainable: bool. If True, this variable weights will be trained.
collections: str. A collection to add the new variable to (optional).
caching_device: str. Optional device string or function describing where the Variable should be cached for reading. Defaults to the Variable's device.
validate_shape: bool. Validate or not shape when restoring.
device: str. Optional device ID to store the variable.
restore: bool. Restore or not this variable when loading a pre-trained model (Only compatible with tflearn pre-built training functions).

A Variable.

get_all_variables

tflearn.variables.get_all_variables ()

Get all Graph variables.

A list of Variables.

tflearn.variables.get_all_trainable_variable ()

Get all Graph trainable variables.

A list of Variables.

tflearn.variables.get_layer_variables_by_name (name)

Retrieve a layer's variables, given its name.

A list of Variables.

tflearn.variables.get_value (var, session=None)

Get a variable's value. If no session provided, use default one.

var: Variable. The variable to get value from.
session: Session. The session to run the op. Default: the default session.

The variable's value.

tflearn.variables.set_value (var, value, session=None)

Set a variable's value. If no session provided, use default one.

var: Variable. The variable to assign a value.
value: The value to assign. Must be compatible with variable dtype.
session: Session. The session to perform the assignation. Default: the default session.