manim_ml.neural_network package#

Subpackages#

Submodules#

manim_ml.neural_network.neural_network module#

Neural Network Manim Visualization

This module is responsible for generating a neural network visualization with manim, specifically a fully connected neural network diagram.

Example

# Specify how many nodes are in each node layer layer_node_count = [5, 3, 5] # Create the object with default style settings NeuralNetwork(layer_node_count)

class manim_ml.neural_network.neural_network.NeuralNetwork(input_layers, layer_spacing=0.2, animation_dot_color='#FF862F', edge_width=2.5, dot_radius=0.03, title=' ', layout='linear', layout_direction='left_to_right', debug_mode=False)#

Bases: Group

Neural Network Visualization Container Class

add_connection(start_mobject_or_name, end_mobject_or_name, connection_style='default', connection_position='bottom', arc_direction='down')#

Add connection from start layer to end layer

animation_overrides = {<class 'manim.animation.creation.Create'>: <function NeuralNetwork._create_override>}#
filter_layers(function)#

Filters layers of the network given function

insert_layer(layer, insert_index)#

Inserts a layer at the given index

make_forward_pass_animation(run_time=None, passing_flash=True, layer_args={}, per_layer_animations=False, **kwargs)#

Generates an animation for feed forward propagation

make_input_layers_dict(input_layers)#

Make dictionary of input layers

remove_layer(layer)#

Removes layer object if it exists

replace_layer(old_layer, new_layer)#

Replaces given layer object

scale(scale_factor, **kwargs)#

Overriden scale

set_z_index(z_index_value: float, family=False)#

Overriden set_z_index

manim_ml.neural_network.neural_network_transformations module#

manim_ml.neural_network.variational_autoencoder module#

Module contents#