问题描述
我使用 pyGAD Python 库提供的遗传算法实现训练了一组神经网络。 到目前为止我编写的代码如下:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import pygad.gann
import time
import pickle
ret = -1
n_sect = 174
population_size = 500
num_parents_mating = 4
num_generations = 1000
mutation_percent = 5
parent_selection_type = "rank"
crossover_type = "two_points"
mutation_type = "random"
keep_parents = 1
init_range_low = -2
init_range_high = 5
n_div = 15
data = pd.read_csv("delta_results/sub_delta_{}.csv".format(n_sect),index_col=0)
data.index = pd.to_datetime(data.index)
data = list(data["Delta"])
function_inputs = np.array([data[i:i+n_div][:ret] for i in range(0,len(data),n_div)])
required_outputs = np.array([[data[i:i+n_div][ret]] for i in range(0,n_div)])
input_layer_size = function_inputs.shape[1]
n_hidden_layers = 2
hidden_layer_1_size = input_layer_size - 2
hidden_layer_2_size = input_layer_size - 4
output_layer_size = 1
population = pygad.gann.GANN(
num_solutions=population_size,num_neurons_input=input_layer_size,num_neurons_output=output_layer_size,num_neurons_hidden_layers=[hidden_layer_1_size,hidden_layer_2_size],# 2 Hidden Layers
hidden_activations=["relu","relu"],output_activation="None"
)
population_vectors = pygad.gann.population_as_vectors(population_networks=population.population_networks)
initial_population = population_vectors.copy()
def normalize(x):
return x/np.linalg.norm(x,ord=2,axis=0,keepdims=True)
def fitness(solution,solution_index):
prediction = pygad.nn.predict(last_layer=population.population_networks[solution_index],data_inputs=function_inputs,problem_type="regression")
prediction = np.array(prediction)
error = (prediction+0.0001)-required_outputs
fitness = np.nan_to_num((np.abs(error)**(-2))).astype(np.float64)
solution_fitness = np.sum(normalize(fitness))
return solution_fitness
def on_generation(population_instance):
global population
population_matrices = pygad.gann.population_as_matrices(population_networks=population.population_networks,population_vectors=population_instance.population)
population.update_population_trained_weights(population_trained_weights=population_matrices)
population_instance = pygad.GA(
num_generations=num_generations,num_parents_mating=num_parents_mating,initial_population=initial_population,fitness_func=fitness,mutation_percent_genes=mutation_percent,init_range_low=init_range_low,init_range_high=init_range_high,parent_selection_type=parent_selection_type,crossover_type=crossover_type,mutation_type=mutation_type,keep_parents=keep_parents,on_generation=on_generation
)
saved_population = pygad.load(filename=".../population_data_v2")
best_solution = saved_population.best_solution()
print("Population Best Solution Info:\n| Attributes:\n{}\n| fitness: {}\n| Solution Index: {}".format(best_solution[0],best_solution[1],best_solution[2]))
saved_population.plot_result()
运行遗传算法后,我将种群数据保存到一个名为 population_data_v2.pkl
的文件中(上面未显示) - 并且该文件已成功创建并保存。
然而,一旦我打开文件,我不知道如何从总体中找到最佳神经网络的信息。
我得到的只是解决方案 (best_solution[0])
的 nd.numpy.array,我不知道如何查询,或者如何传入函数输入,看看最佳解决方案的预测是什么.
任何帮助将不胜感激!
解决方法
感谢您使用 PyGAD。
我看到您正确构建了示例。您可以通过简单的 3 个步骤轻松使用最佳解决方案进行预测。
请注意,在每一代之后,population
属性都会由最新的种群更新。这意味着在 PyGAD 完成所有世代后,最后一个种群保存在 population
属性中。
步骤 1
在您使用 pygad.load()
函数加载保存的模型后,就像您在适应度函数中所做的那样,您可以使用 population
属性来恢复网络的权重,如下所示:
population_matrices = pygad.gann.population_as_matrices(population_networks=population.population_networks,population_vectors=saved_population.population)
population.update_population_trained_weights(population_trained_weights=population_matrices)
步骤 2
best_solution()
方法返回 3 个输出,其中第三个表示最佳解决方案的索引。您可以使用它进行如下预测:
best_solution = saved_population.best_solution()
prediction = pygad.nn.predict(last_layer=population.population_networks[best_solution[2]],data_inputs=function_inputs,problem_type="regression")
步骤 3
最后,您可以打印预测值:
prediction = np.array(prediction)
print("Prediction of the best solution: {pred}".format(pred=prediction))
完整代码
在上述讨论中,以下是可让您根据最佳解决方案进行预测的代码:
population_matrices = pygad.gann.population_as_matrices(population_networks=population.population_networks,population_vectors=saved_population.population)
population.update_population_trained_weights(population_trained_weights=population_matrices)
best_solution = saved_population.best_solution()
prediction = pygad.nn.predict(last_layer=population.population_networks[best_solution[2]],problem_type="regression")
prediction = np.array(prediction)
print("Prediction of the best solution: {pred}".format(pred=prediction))
如果出现问题,请告诉我。
再次感谢您使用 PyGAD。