一个跨平台的易于访问的人工智能工具库
ingine的Python项目详细描述
ingine-一个跨平台的ai工具箱
功能
- 人工神经网络：
- 分类器生成器；
- 回归生成器；
- 自定义图层生成器；
- 定制路缘石通道。
- 进化算法；
现成示例
- 8皇后拼图；
- 肖巴特勒·安；
- 手写数字识别ann；
- 波士顿住房；
- 销售人员问题解决；
怎么做？
分类：
fromingineimportann"""getting dataset"""(X_train,Y_train),(X_test,Y_test)=get_dataset()categorizer=ann.get_categorizer(X_train,y_train,num_cat=10)"""check out how it works!"""print(categorizer(X_train[0]),Y_train[0])
回归：
fromingineimportann"""getting dataset"""(X_train,Y_train),(X_test,Y_test)****=get_dataset()regression=ann.get_regression(X_train,y_train)"""check out how it works!"""print(regression(X_train[0]),Y_train[0])
自定义层配置：
fromingineimportannfromkeras.layersimportDense"""getting dataset"""(X_train,Y_train),(X_test,Y_test)=get_dataset()# defining layerslayers=[Dense(100,input_dim=100,activation="softsign",kernel_initializer="normal"),Dense(20,activation="softsign",kernel_initializer="normal"),Dense(10,activation="softsign",kernel_initializer="normal"),Dense(100,activation="softsign",kernel_initializer="normal")]customnn=ann.get_customnn(X_train,Y_train,layers=layers)"""check out how it works!"""print(customnn(X_train[0]),Y_train[0])
进化优化器：
fromingineimportgaimportrandomasrnd"""define an example creature"""data=[1,2,3,4]"""define a representation function of creature"""defcreate_individual(data):returndata[:]"""define a crossover function"""defcrossover(creature1,creature2):r1=[rnd.randint(1,10)for_inrange(4)]r2=[rnd.randint(1,10)for_inrange(4)]returnr1,r2"""define an mutation function"""defmutate(creature):a=rnd.randint(0,len(creature)-1)b=rnd.randint(0,len(creature)-1)creature[a],creature[b]=creature[a]+1,creature[b]+1"""define a selection function"""defselection(population):returnrnd.choice(population)"""define a fitness function"""deffitness(creature,data):returnabs(sum(creature)-100)"""getting an optimizer"""optimiser=ga.get_optimizer(data,fitness,maximise_fitness=False,create_individual=create_individual,mutate=mutate,crossover=crossover)"""check out how it works!"""res=optimiser()[1]
欢迎加入QQ群-->： 979659372
