brainpy.nn.base.FrozenNetwork
brainpy.nn.base.FrozenNetwork#
- class brainpy.nn.base.FrozenNetwork(nodes=None, ff_edges=None, fb_edges=None, **kwargs)[source]#
A FrozenNetwork is a Network that can not be linked to other nodes or networks.
- __init__(nodes=None, ff_edges=None, fb_edges=None, **kwargs)#
Methods
__init__
([nodes, ff_edges, fb_edges])copy
([name, shallow])Returns a copy of the Node.
feedback
(ff_output, **shared_kwargs)The feedback computation function of a node.
forward
(ff[, fb, forced_states, ...])The main computation function of a network.
get_node
(name)init_fb_conn
()Initialize the feedback connections of the network.
init_fb_output
([num_batch])Set the initial node feedback state.
init_ff_conn
()Initialize the feedforward connections of the network.
init_state
([num_batch])Set the initial node state.
initialize
([num_batch])Initialize the whole network.
load_states
(filename[, verbose])Load the model states.
nodes
([method, level, include_self])Collect all children nodes.
offline_fit
(targets, ffs[, fbs])Offline training interface.
online_fit
(target, ff[, fb])Online training fitting interface.
online_init
()Online training initialization interface.
plot_node_graph
([fig_size, node_size, ...])Plot the node graph based on NetworkX package
register_implicit_nodes
(nodes)register_implicit_vars
(variables)replace_graph
(nodes, ff_edges[, fb_edges])save_states
(filename[, variables])Save the model states.
set_fb_output
(state)Safely set the feedback state of the node.
set_feedback_shapes
(fb_shapes)set_feedforward_shapes
(feedforward_shapes)set_output_shape
(shape)set_state
(state)Safely set the state of the node.
train_vars
([method, level, include_self])The shortcut for retrieving all trainable variables.
unique_name
([name, type_])Get the unique name for this object.
update_graph
(new_nodes, new_ff_edges[, ...])Update current Model's with new nodes and edges, inplace (a copy is not performed).
vars
([method, level, include_self])Collect all variables in this node and the children nodes.
Attributes
data_pass
Offline fitting method.
entry_nodes
First Nodes in the graph held by the Model.
exit_nodes
Last Nodes in the graph held by the Model.
fb_edges
fb_output
fb_receivers
Nodes which receive feedback connections.
fb_senders
Nodes which project feedback connections.
feedback_nodes
Nodes which project feedback connections.
feedback_shapes
Output data size.
feedforward_shapes
Input data size.
ff_edges
ff_receivers
Nodes which receive feedforward connections.
ff_senders
Nodes which project feedforward connections.
is_feedback_input_supported
is_feedback_supported
is_initialized
- rtype
lnodes
name
nodes_has_feedback
Nodes which receive feedback connections.
output_shape
Output data size.
state
Node current internal state.
trainable
Returns True if at least one Node in the Model is trainable.