使用 keras 的 sk-learn API 时出错

Question

  这些天我正在学习keras，在使用scikit-learn API时遇到了一个错误。这里有一些可能有用的东西:

:

python:3.5.2  
keras:1.0.5  
scikit-learn:0.17.1

import pandas as pd
from keras.layers import Input, Dense
from keras.models import Model
from keras.models import Sequential
from keras.wrappers.scikit_learn import KerasRegressor
from sklearn.cross_validation import train_test_split
from sklearn.cross_validation import cross_val_score
from sqlalchemy import create_engine
from sklearn.cross_validation import KFold

def read_db():
    "get prepared data from mysql."
    con_str = "mysql+mysqldb://root:0000@localhost/nbse?charset=utf8"
    engine = create_engine(con_str)
    data = pd.read_sql_table('data_ml', engine)
    return data
def nn_model():
    "create a model."
    model = Sequential()
    model.add(Dense(output_dim=100, input_dim=105, activation='softplus'))
    model.add(Dense(output_dim=1, input_dim=100, activation='softplus'))
    model.compile(loss='mean_squared_error', optimizer='adam')
    return model
data = read_db()
y = data.pop('PRICE').as_matrix()
x = data.as_matrix()
model = nn_model()
model = KerasRegressor(build_fn=model, nb_epoch=2)
model.fit(x,y)  #something wrong here!

误差

Traceback (most recent call last):
  File "C:/Users/Administrator/PycharmProjects/forecast/gridsearch.py", line 43, in <module>
    model.fit(x,y)
  File "D:Program FilesPython35libsite-packageskeraswrappersscikit_learn.py", line 135, in fit
    **self.filter_sk_params(self.build_fn.__call__))
TypeError: __call__() missing 1 required positional argument: 'x'
Process finished with exit code 1

该模型在没有kerasRegressor包装的情况下工作得很好，但我想在此之后使用sk_learn的gridSearch，所以我在这里寻求帮助。我试过了，但还是不知道。

keras.warappers.scikit_learn.py  
class BaseWrapper(object):  

    def __init__(self, build_fn=None, **sk_params):
        self.build_fn = build_fn
        self.sk_params = sk_params
        self.check_params(sk_params)  

    def fit(self, X, y, **kwargs):
        '''Construct a new model with build_fn and fit the model according
        to the given training data.
    # Arguments
        X : array-like, shape `(n_samples, n_features)`
            Training samples where n_samples in the number of samples
            and n_features is the number of features.
        y : array-like, shape `(n_samples,)` or `(n_samples, n_outputs)`
            True labels for X.
        kwargs: dictionary arguments
            Legal arguments are the arguments of `Sequential.fit`
    # Returns
        history : object
            details about the training history at each epoch.
    '''
    if self.build_fn is None:
        self.model = self.__call__(**self.filter_sk_params(self.__call__))
    elif not isinstance(self.build_fn, types.FunctionType):
        self.model = self.build_fn(
            **self.filter_sk_params(self.build_fn.__call__))
    else:
        self.model = self.build_fn(**self.filter_sk_params(self.build_fn))
    loss_name = self.model.loss
    if hasattr(loss_name, '__name__'):
        loss_name = loss_name.__name__
    if loss_name == 'categorical_crossentropy' and len(y.shape) != 2:
        y = to_categorical(y)
    fit_args = copy.deepcopy(self.filter_sk_params(Sequential.fit))
    fit_args.update(kwargs)
    history = self.model.fit(X, y, **fit_args)
    return history

  

    self.model = self.build_fn(
        **self.filter_sk_params(self.build_fn.__call__))

自我。build_fn这里是keras.models.Sequential

models.py  
class Sequential(Model):
    def call(self, x, mask=None):
        if not self.built:
            self.build()
        return self.model.call(x, mask)

那么，x是什么意思，如何修复这个错误?
谢谢!

Answer 1

xiao，我也遇到了同样的问题!希望这对你有所帮助:

背景与议题

Keras的文档指出，在为scikit-learn实现包装器时，有两个参数。第一个是构建函数，它是一个"可调用函数"或"类实例"。具体来说，它声明:

build_fn应该构造、编译并返回一个Keras模型，然后该模型将用于拟合/预测。可以将以下三个值中的一个传递给build_fn:

2. 实现call方法的类实例
3. 。这意味着你实现了一个从KerasClassifier或KerasRegressor继承的类。当前类的call方法将被视为默认的build_fn。

在您的代码中，您创建模型，然后在创建KerasRegressor包装器时将模型作为参数build_fn的值传递:

model = nn_model()
model = KerasRegressor(build_fn=model, nb_epoch=2)

问题就在这里。不是传递nn_model 函数作为build_fn，而是传递Keras Sequential模型的实际实例。因此，当调用fit()时，它找不到call方法，因为它没有在您返回的类中实现。

<标题>解决方案

我所做的使事情工作是传递函数作为build_fn，而不是一个实际的模型:

data = read_db()
y = data.pop('PRICE').as_matrix()
x = data.as_matrix()
# model = nn_model() # Don't do this!
# set build_fn equal to the nn_model function
model = KerasRegressor(build_fn=nn_model, nb_epoch=2) # note that you do not call the function!
model.fit(x,y)  # fixed!

这不是唯一的解决方案(您可以将build_fn设置为适当实现call方法的类)，但这对我来说是有效的。我希望它能帮助你!

Answer 2

传递给__init__()的自定义关键字参数，也就是说，所有给__init__()的关键字参数将直接传递给model_build_fn。例如，调用KerasClassifier(myparam=10)将导致model_build_fn(my_param=10)

这里有一个例子:

class MyMultiOutputKerasRegressor(KerasRegressor):
    
    # initializing
    def __init__(self, **kwargs):
        KerasRegressor.__init__(self, **kwargs)
        
    # simpler fit method
    def fit(self, X, y, **kwargs):
        KerasRegressor.fit(self, X, [y]*3, **kwargs)

(…)

def get_quantile_reg_rpf_nn(layers_shape=[50,100,200,100,50], inDim= 4, outDim=1, act='relu'):
          # do model stuff...

(…)初始化Keras回归量:

base_model = MyMultiOutputKerasRegressor(build_fn=get_quantile_reg_rpf_nn,
                                         layers_shape=[50,100,200,100,50], inDim= 4, 
                                         outDim=1, act='relu', epochs=numEpochs, 
                                         batch_size=batch_size, verbose=0)