python - How to visualize a neural network -
i want draw dynamic picture neural network watch weights changed , activation of neurons during learning. how simulate process in python?
more precisely, if network shape is: [1000, 300, 50], wish draw 3 layer nn contains 1000, 300 , 50 neurons respectively. further, hope picture reflect saturation of neurons on each layer during each epoch.
i've no idea how it. can shed light on me?
i adapted parts answer of milo
from matplotlib import pyplot math import cos, sin, atan class neuron(): def __init__(self, x, y): self.x = x self.y = y def draw(self, neuron_radius): circle = pyplot.circle((self.x, self.y), radius=neuron_radius, fill=false) pyplot.gca().add_patch(circle) class layer(): def __init__(self, network, number_of_neurons, number_of_neurons_in_widest_layer): self.vertical_distance_between_layers = 6 self.horizontal_distance_between_neurons = 2 self.neuron_radius = 0.5 self.number_of_neurons_in_widest_layer = number_of_neurons_in_widest_layer self.previous_layer = self.__get_previous_layer(network) self.y = self.__calculate_layer_y_position() self.neurons = self.__intialise_neurons(number_of_neurons) def __intialise_neurons(self, number_of_neurons): neurons = [] x = self.__calculate_left_margin_so_layer_is_centered(number_of_neurons) iteration in xrange(number_of_neurons): neuron = neuron(x, self.y) neurons.append(neuron) x += self.horizontal_distance_between_neurons return neurons def __calculate_left_margin_so_layer_is_centered(self, number_of_neurons): return self.horizontal_distance_between_neurons * (self.number_of_neurons_in_widest_layer - number_of_neurons) / 2 def __calculate_layer_y_position(self): if self.previous_layer: return self.previous_layer.y + self.vertical_distance_between_layers else: return 0 def __get_previous_layer(self, network): if len(network.layers) > 0: return network.layers[-1] else: return none def __line_between_two_neurons(self, neuron1, neuron2): angle = atan((neuron2.x - neuron1.x) / float(neuron2.y - neuron1.y)) x_adjustment = self.neuron_radius * sin(angle) y_adjustment = self.neuron_radius * cos(angle) line = pyplot.line2d((neuron1.x - x_adjustment, neuron2.x + x_adjustment), (neuron1.y - y_adjustment, neuron2.y + y_adjustment)) pyplot.gca().add_line(line) def draw(self, layertype=0): neuron in self.neurons: neuron.draw( self.neuron_radius ) if self.previous_layer: previous_layer_neuron in self.previous_layer.neurons: self.__line_between_two_neurons(neuron, previous_layer_neuron) # write text x_text = self.number_of_neurons_in_widest_layer * self.horizontal_distance_between_neurons if layertype == 0: pyplot.text(x_text, self.y, 'input layer', fontsize = 12) elif layertype == -1: pyplot.text(x_text, self.y, 'output layer', fontsize = 12) else: pyplot.text(x_text, self.y, 'hidden layer '+str(layertype), fontsize = 12) class neuralnetwork(): def __init__(self, number_of_neurons_in_widest_layer): self.number_of_neurons_in_widest_layer = number_of_neurons_in_widest_layer self.layers = [] self.layertype = 0 def add_layer(self, number_of_neurons ): layer = layer(self, number_of_neurons, self.number_of_neurons_in_widest_layer) self.layers.append(layer) def draw(self): pyplot.figure() in range( len(self.layers) ): layer = self.layers[i] if == len(self.layers)-1: = -1 layer.draw( ) pyplot.axis('scaled') pyplot.axis('off') pyplot.title( 'neural network architecture', fontsize=15 ) pyplot.show() class drawnn(): def __init__( self, neural_network ): self.neural_network = neural_network def draw( self ): widest_layer = max( self.neural_network ) network = neuralnetwork( widest_layer ) l in self.neural_network: network.add_layer(l) network.draw() now layers labeled, axis deleted , constructing plot easier. it's done by:
network = plotnn.drawnn( [2,8,8,1] ) network.draw() here net following structure constructed:
- 2 neurons in input layer
- 8 neurons in 1st hidden layer
- 8 neurons in 2nd hidden layer
- 1 neuron in output layer
