laymon

Top-level package for PyLaymon.

Package Contents

Classes

FeatureMapMonitoring() A wrapper class for adding a model or model layers for monitoring the feature maps
FeatureMapObserver(layer, layer_name, update_display) An class used to create observers that are used to monitor the feature maps of the given layer.
FeatureMapDisplay() A class for defining methods for displaying the parameters being monitored by a FeatureMapObserver.
FeatureMapMonitor() A monitor type class for visualizing the feature maps of a neural network.
class laymon.FeatureMapMonitoring[source]

Bases: object

A wrapper class for adding a model or model layers for monitoring the feature maps during training of the model.

add_layer(self, layer, layer_name)

Adds the layer whose feature maps are to be monitored. :param layer: pyTorch layer :param layer_name: (str) name of the layer :return: the observer object of the layer being monitored

_add_layer(self, layer, layer_name)

Create a observer class of the layer to be monitored and adds it to the list of observers being monitored. :param layer: pyTorch layer :param layer_name: (str) name of the layer :return: Observer object of the layer

_remove_layer(self, layer_name)

Removes an observer from the list of observers being monitored. :param layer_name: name of the observer :return: True if observer was deleted, else False

remove_layer(self, layer_name)

Remove the layer from list of layer being monitored. :param layer_name: str (name of the layer) :return: True if the layer is deleted from the list of monitored objects, else False

add_model(self, model)

Registers all the layers a pyTorch model whose activations maps are to monitored. :param model: :return:

start(self)

Starts monitoring the feature maps of the registered layers/model.

class laymon.FeatureMapObserver(layer, layer_name, update_display)[source]

Bases: laymon.interfaces.Observer

An class used to create observers that are used to monitor the feature maps of the given layer.

update(self, parameters)

Update the display attached to the observer with the new parameters/activations. :param parameters: Tensor :return: None

get_layer_name(self)

Returns the layer name being observed.

get_layer(self)

Returns the layer object being observed.

class laymon.FeatureMapDisplay

Bases: laymon.interfaces.Display

A class for defining methods for displaying the parameters being monitored by a FeatureMapObserver.

display_params(self, activation, max_subplots=5)

Method for updating the subplots and figure with the new parameters (activation maps).

_show(self)
update_display(self, parameters, display_title)

Updates the display with the new parameters :param parameters: Tensor (activation map params) :param display_title: Title of the figure

class laymon.FeatureMapMonitor

Bases: laymon.interfaces.Monitor

A monitor type class for visualizing the feature maps of a neural network.

add_observer(self, layer_observer)
  1. Creates a layer observer object.
  2. Hooks the layer to capture the activation map of the layer.
  3. Adds the observer object to the list of monitored observers.
Parameters:layer_observer – Observer object
remove_observer(self, layer_observer=None, layer_name=None)
If the layer observer/layer name is in the list of monitored observers:
  1. Unhook the layer.
  2. Remove the layer observer from the list of monitored observers.
Parameters:
  • layer_observer – Layer Observer.
  • layer_name – Name of the layer being monitored.
Returns:

True/False based on whether the observer by deleted or not.
static _is_layer_single_dim(layer)

Checks if the layer is a single dimensional layer

_get_activation_map(self, layer_name)

Hooks the layer to capture activation maps for the given layer and return the handler to the hook

notify_observers(self)

Updates all the observers being monitored with the new parameters

get_registered_observers(self)

Returns the list of observers being monitored.

laymon.__author__ = Shubham Gupta[source]
laymon.__email__ = shubhamgupta3121@gmail.com[source]
laymon.__version__ = 1.0.0[source]