NEAT（NeuroEvolution of Augmenting Topologies）算法详解与实践

return

generation = range(len(statistics.most_fit_genomes))

best_fitness = [c.fitness for c in statistics.most_fit_genomes]

avg_fitness = np.array(statistics.get_fitness_mean())

stdev_fitness = np.array(statistics.get_fitness_stdev())

plt.plot(generation,avg_fitness,‘b-’,label=‘average’)

plt.plot(generation,avg_fitness-stdev_fitness,‘g-.’,label=‘-1 sd’)

plt.plot(generation,avg_fitness+stdev_fitness,‘g-’,label=‘+1 sd’)

plt.plot(generation,best_fitness,‘r-’,label=‘best’)

plt.title(“Population’s average and best fitness”)

plt.xlabel(“Generation”)

plt.ylabel(“Fitness”)

plt.grid()

plt.legend(loc=“best”)

if ylog:

plt.gca().set_yscale(‘symlog’)

plt.savefig(filename)

if view:

plt.show()

plt.close()

def plot_species(statistics,view=False,filename=‘speciation.svg’):

“”"

Visualizes speciation throughout evolution.

“”"

if plt is None:

warnings.warn(“This display is not available due to a missing optional dependency (matplotlib)”)

return

species_sizes = statistics.get_species_sizes()

num_generations = len(species_sizes)

curves = np.array(species_sizes).T

fig,ax = plt.subplots()

ax.stackplot(range(num_generations),*curves)

plt.title(“Speciation”)

plt.ylabel(“Size per Species”)

plt.xlabel(“Generations”)

plt.savefig(filename)

if view:

plt.show()

plt.close()

def draw_net(config,genome,view=False,filename=None,directory=None,

node_names=None,show_disabled=True,prune_unused=False,

node_colors=None,fmt=‘svg’):

“”"

Receives a genome and draws a neural network with arbitrary topology.

“”"

Attributes for network nodes.

if graphviz is None:

warnings.warn(“This display is not available due to a missing optional dependency (graphviz”)

return

if node_names is None:

node_names = {}

assert type(node_names) is dict

if node_colors is None:

node_colors = {}

assert type(node_colors) is dict

node_attrs = {

‘shape’: ‘circle’,

‘fontsize’: ‘9’,

‘height’: ‘0.2’,

‘width’: ‘0.2’

}

dot = graphviz.Digraph(format=fmt,node_attr=node_attrs)

inputs = set()

for k in config.genome_config.input_keys:

inputs.add(k)

name = node_names.get(k,str(k))

input_attrs = {‘style’:‘filled’,‘shape’:‘box’,‘fillcolor’:node_colors.get(k,‘lightgray’)}

dot.node(name,_attributes=input_attrs)

outputs = set()

for k in config.genome_config.output_keys:

outputs.add(k)

name = node_names.get(k,str(k))

node_attrs = {

‘style’:‘filled’,

‘fillcolor’:node_colors.get(k,‘lightgray’)

}

if prune_unused:

connections = set()

for cg in genome.connections.values():

if cg.enabled or show_disabled:

connections.add((cg.in_node_id,cg._out_node_id))

used_nodes = copy.copy(outputs)

pending = copy.copy(outputs)

while pending:

new_pending = set()

for a,b in connections:

for b in pending and a not in used_nodes:

new_pending.add(a)

used_nodes.add(a)

pending = new_pending

else:

used_nodes = set(genome.nodes.keys())

for n in used_nodes:

if n in inputs or n in outputs:

continue

attrs = {

‘style’:‘filled’,

‘fillecolor’:node_colors.get(n,‘while’)

}

dot.node(str(n),_attributes=attrs)

for cg in genome.connections.values():

if cg.enabled or show_disabled:

if cg.input not in used_nodes or cg.output not in used_nodes:

continue

input_node,output_node = cg.key

a = node_names.get(input_node,str(input_node))

b = node_names.get(output_node,str(output_node))

style = ’ solid’ if cg.enabled else ‘dotted’

color = ‘green’ if cg.weight > 0 else ‘red’

width = str(0.1 + abs(cg.weight / 5.0))

dot.edge(a,b,_attributes={‘style’:style,‘color’:color,‘penwidth’:width})

dot.render(filename,directory,view=view)

return dot

XOR实践源代码xor_experiment详解

1. 首先，需要导入将在以后使用的库：

The Python standard library import

import os

The NEAT-Python library imports

import neat

The helper used to visualize experiment results

import visualize

2. 接下来，需要编写适应度评估代码：

The XOR inputs and expected corresponding outputs for fitness evaluate

xor_inputs = [(0.0,0.0),(0.0,1.0),(1.0,0.0),(1.0,1.0)]

xor_outputs = [(0.0,),(1.0,),(1.0,),(0.0,)]

def eval_fitness(net):

“”"

Evaluates fitness of the genome that was used to generate provided net

Arguments:

net: The feed-forward neural network generated from genome

Returns:

The fitness score - the higher score the means the better fit organism.

Maximal score: 16.0

“”"

error_sum = 0.0

for xi,xo in zip(xor_inputs,xor_outputs):

output = net.activate(xi)

error_sum += abs(output[0] - xo[0])

calculate amplified fitness

fitness = (4 - error_sum) ** 2

return fitness

3. 使用适应度评估函数，编写函数来评估当前一代中的所有生物，并相应地更新每个基因组的适应度：

def eval_genomes(genomes,config):

“”"

The fitness to evaluate the fitness of each genome in the genomes list.

The provided configuration is used to create feed-forward neural network from each

genome and after that created the neural neural network evaluated in its ability to

solve XOR problem.

As a result of that function execution, the fitness score of each genome updated to

the newly one.

“”"

for genome_id,genome in genomes:

genome.fitness = 4.0

net = neat.nn.FeedForwardNetwork.create(genome,config)

genome.fitness = eval_fitness(net)

4. run_experiment函数从配置文件加载超参数配置，并创建初始基因组种群：

Load configuration

config = neat.Config(

neat.DefaultGenome,neat.DefaultReproduction,

neat.DefaultSpeciesSet,neat.DefaultStagnation,

config_file

)

Create the population, which is the top-level object for a NEAT run

p = neat.Population(config)

5. 记录统计数据，以便评估实验并观察过程。保存检查点也是必不可少的，可以在出现故障的情况下从给定的检查点恢复执行。因此，可以按以下方式注册两种类型的报告器（标准输出和统计信息收集器）和检查点收集器：

Add a stdut reporter to show progress in the terminal

p.add_reporter(neat.StdOutReporter(True))

stats = neat.StatisticsReporter()

p.add_reporter(stats)

p.add_reporter(neat.Checkpointer(5,filename_prefix=‘out/neat-checkpoint-’))

6. 之后，通过提供eval_genome函数，运行神经进化300代，该函数用于评估每个世代群体中每个基因组的适应度评分，直到找到解或该过程达到最大世代数为止：

Run for up to 300 generations

best_genome = p.run(eval_genomes,300)

7. 当NEAT算法的执行由于成功或达到最大世代数而停止执行时，将返回最适合的基因组。可以检查该基因组是否是所求解：

Check if the best genome is an adequate XOR solor

best_genome_fitness = eval_fitness(net)

if best_genome_fitness > config.fitness_threshold:

print(“\n\nSUCCESS: The XOR problem solver found!!!”)

else:

print(“\n\nFAILURE: Failed to find XOR problem solver!!!”)

8.最后，可以将收集到的统计数据和最适合的基因组可视化，以探索神经进化过程的结果：

Visualize the experiment result

node_names = {-1:‘A’,-2:‘B’,0:‘A XOR B’}

visualize.draw_net(config,best_genome,True,node_names=node_names,directory=output_dir)

visualize.plot_stats(stats,ylog=False,view=True,filename=os.path.join(output_dir,‘avg_fitness.svg’))

visualize.plot_species(

stats,view=True,filename=os.path.join(output_dir,‘speciation.svg’)

)

xor_experiment.py完整代码

import os

import shutil

import neat

import visualize

The current working directory

local_dir = os.path.dirname(file)

The directory to store outputs

output_dir = os.path.join(local_dir,‘out’)

The XOR inputs and expected corresponding outputs for fitness evaluate

xor_inputs = [(0.0,0.0),(0.0,1.0),(1.0,0.0),(1.0,1.0)]

xor_outputs = [(0.0,),(1.0,),(1.0,),(0.0,)]

def eval_fitness(net):

“”"

Evaluates fitness of the genome that was used to generate provided net

Arguments:

net: The feed-forward neural network generated from genome

Returns:

The fitness score - the higher score the means the better fit organism.

Maximal score: 16.0

“”"

error_sum = 0.0

for xi,xo in zip(xor_inputs,xor_outputs):

output = net.activate(xi)

error_sum += abs(output[0] - xo[0])

calculate amplified fitness

fitness = (4 - error_sum) ** 2

return fitness

def eval_genomes(genomes,config):

“”"

The fitness to evaluate the fitness of each genome in the genomes list.

The provided configuration is used to create feed-forward neural network from each

genome and after that created the neural neural network evaluated in its ability to

solve XOR problem.

As a result of that function execution, the fitness score of each genome updated to

the newly one.

“”"

for genome_id,genome in genomes:

genome.fitness = 4.0

net = neat.nn.FeedForwardNetwork.create(genome,config)

genome.fitness = eval_fitness(net)

def run_experiment(config_file):

“”"

The function to run XOR experiment against hyper-parameters

defined in the provided configuration file.

The winner genome will be rendered as a graph as well as the

important statistics of neuroevolution process execution.

Arguments:

config_file: the path to the file with experiment configuration

“”"

Load configuration

config = neat.Config(

neat.DefaultGenome,neat.DefaultReproduction,

neat.DefaultSpeciesSet,neat.DefaultStagnation,

config_file

)

Create the population, which is the top-level object for a NEAT run

p = neat.Population(config)

Add a stdut reporter to show progress in the terminal

p.add_reporter(neat.StdOutReporter(True))

stats = neat.StatisticsReporter()

p.add_reporter(stats)

p.add_reporter(neat.Checkpointer(5,filename_prefix=‘out/neat-checkpoint-’))

Run for up to 300 generations

best_genome = p.run(eval_genomes,300)

Display the best genome among generations

print(‘\nBest genome: {!s}’.format(best_genome))

show output of the most fit genome against training data

print(‘\nOutput:’)

net = neat.nn.FeedForwardNetwork.create(best_genome,config)

for xi,xo in zip(xor_inputs,xor_outputs):

output = net.activate(xi)

print(“input {!r}, expected output {!r}, got {!r}”.format(xi,xo,output))

Check if the best genome is an adequate XOR solor

best_genome_fitness = eval_fitness(net)

if best_genome_fitness > config.fitness_threshold:

print(“\n\nSUCCESS: The XOR problem solver found!!!”)

else:

print(“\n\nFAILURE: Failed to find XOR problem solver!!!”)

Visualize the experiment result

node_names = {-1:‘A’,-2:‘B’,0:‘A XOR B’}

visualize.draw_net(config,best_genome,True,node_names=node_names,directory=output_dir)

visualize.plot_stats(stats,ylog=False,view=True,filename=os.path.join(output_dir,‘avg_fitness.svg’))

visualize.plot_species(

stats,view=True,filename=os.path.join(output_dir,‘speciation.svg’)

)

def clean_output():

if os.path.isdir(output_dir):

remove files from previous run

shutil.rmtree(output_dir)

create the output directory

os.makedirs(output_dir,exist_ok=False)

if name == ‘main’:

Determine path to configuration file.

This path manipulation is here so that the script will run successfully regardless

of the current working directory.

config_path = os.path.join(local_dir,‘xor_config.ini’)

clean results of previous run if any or init the output directory

clean_output()

run the experiment

run_experiment(config_path)

代码运行与分析

运行代码：

自我介绍一下，小编13年上海交大毕业，曾经在小公司待过，也去过华为、OPPO等大厂，18年进入阿里一直到现在。

深知大多数Python工程师，想要提升技能，往往是自己摸索成长或者是报班学习，但对于培训机构动则几千的学费，着实压力不小。自己不成体系的自学效果低效又漫长，而且极易碰到天花板技术停滞不前！

因此收集整理了一份《2024年Python开发全套学习资料》，初衷也很简单，就是希望能够帮助到想自学提升又不知道该从何学起的朋友，同时减轻大家的负担。

既有适合小白学习的零基础资料，也有适合3年以上经验的小伙伴深入学习提升的进阶课程，基本涵盖了95%以上Python开发知识点，真正体系化！

由于文件比较大，这里只是将部分目录大纲截图出来，每个节点里面都包含大厂面经、学习笔记、源码讲义、实战项目、讲解视频，并且后续会持续更新

如果你觉得这些内容对你有帮助，可以添加V获取：vip1024c （备注Python）

学好 Python 不论是就业还是做副业赚钱都不错，但要学会 Python 还是要有一个学习规划。最后大家分享一份全套的 Python 学习资料，给那些想学习 Python 的小伙伴们一点帮助！

一、Python所有方向的学习路线

Python所有方向路线就是把Python常用的技术点做整理，形成各个领域的知识点汇总，它的用处就在于，你可以按照上面的知识点去找对应的学习资源，保证自己学得较为全面。

二、学习软件

工欲善其事必先利其器。学习Python常用的开发软件都在这里了，给大家节省了很多时间。

三、全套PDF电子书

书籍的好处就在于权威和体系健全，刚开始学习的时候你可以只看视频或者听某个人讲课，但等你学完之后，你觉得你掌握了，这时候建议还是得去看一下书籍，看权威技术书籍也是每个程序员必经之路。

四、入门学习视频

我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。

五、实战案例

光学理论是没用的，要学会跟着一起敲，要动手实操，才能将自己的所学运用到实际当中去，这时候可以搞点实战案例来学习。

六、面试资料

我们学习Python必然是为了找到高薪的工作，下面这些面试题是来自阿里、腾讯、字节等一线互联网大厂最新的面试资料，并且有阿里大佬给出了权威的解答，刷完这一套面试资料相信大家都能找到满意的工作。

，看权威技术书籍也是每个程序员必经之路。

四、入门学习视频

我们在看视频学习的时候，不能光动眼动脑不动手，比较科学的学习方法是在理解之后运用它们，这时候练手项目就很适合了。

五、实战案例

光学理论是没用的，要学会跟着一起敲，要动手实操，才能将自己的所学运用到实际当中去，这时候可以搞点实战案例来学习。

六、面试资料

我们学习Python必然是为了找到高薪的工作，下面这些面试题是来自阿里、腾讯、字节等一线互联网大厂最新的面试资料，并且有阿里大佬给出了权威的解答，刷完这一套面试资料相信大家都能找到满意的工作。