Skip to main content
 首页 » 编程设计

python之如何通过 Keras Wrapper(或一般)传递参数

2024年11月01日30langtianya

我有以下模型,我想通过 GridSearchCV() 调整多个参数。到目前为止它可以工作,但我无法以相同的方式调整 compile() 的参数:

def create_model(activation='relu' 
                 , init='he_normal'  
                 , loss = 'mean_squared_error'  
                 , optimizer = 'adam'  
                 , metrics=['accuracy']  
                 , dropout_rate= 0 
                 , learning_rate = 0.1 
                 , decay_rate = 0.005 
                 , momentum = 0.8 
                ): 
 
    # Model definition 
    model = Sequential() 
    model.add(Dense(16, input_shape=(2, ),  
                    activation = activation, 
                    kernel_initializer = init))          
                 .... 
 
    model.add(Dropout(dropout_rate)) 
    model.add(Dense(2,  
                    activation = "tanh")) 
 
    # Compile model  
    model.compile(loss = 'mean_squared_error' 
                  , optimizer = 'adam' 
                                      # ( 
                                      #  learning_rate = learning_rate 
                                      # , decay_rate = decay_rate 
                                      # , momentum =momentum 
                                      # ) 
                  , metrics = ['accuracy'] 
                 ) 
 
    return model 
 
# define the grid search parameters 
batch_size = [2, 6] 
epochs = [5, 10] 
activation = ['relu', 'tanh']     
optimizer = ['Adam', 'sgd']     
metrics = ['mse', 'acc'] 
loss = ['mse', 'mae']  
dropout_rate = [0.1, 0.25] 
learning_rate = [0.2, 0.3] 
decay_rate = [0.001, 0.005] 
momentum = [0.4, 0.7] 
kernel_initializer = ['init', 'normal'] 
 
param_grid = dict(batch_size=batch_size 
                      , epochs=epochs 
                      , activation = activation 
                      , optimizer = optimizer 
                      , metrics = metrics 
                      , loss = loss         
                      , dropout_rate = dropout_rate  
                      , learning_rate = learning_rate 
                      , decay_rate = decay_rate 
                      , momentum = momentum 
                      , kernel_initializer = kernel_initializer 
                     ) 
 
hypparas = param_grid 
 
model = KerasRegressor(build_fn=create_model, verbose=0) 
 
model_cv = GridSearchCV(estimator=model,  
                    param_grid=hypparas,  
                    n_jobs=1,    # -1 uses all cores 
                    cv=5 
                    ) 
 
model_cv_result = model_cv.fit(X, y) 

并且我想将 learning_rate、decay_rate 和 momentum 添加到要调整的超参数中。但它不像上面那样工作(这就是为什么我取消注释 compile() 中的特定行。 我必须分别更改什么?如何将这些参数传递给 create_model()?

编辑:

> model_cv_result = model_cv.fit(X, y) 
 
:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py:266: UserWarning: The total space of parameters 4 is smaller than n_iter=20. Running 4 iterations. For exhaustive searches, use GridSearchCV. 
  % (grid_size, self.n_iter, grid_size), UserWarning) 
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py:528: FutureWarning: From version 0.22, errors during fit will result in a cross validation score of NaN by default. Use error_score='raise' if you want an exception raised or error_score=np.nan to adopt the behavior from version 0.22. 
  FutureWarning) 
--------------------------------------------------------------------------- 
ValueError                                Traceback (most recent call last) 
<ipython-input-256-703cbc43fc8b> in <module> 
----> 5 model_cv_result = model_cv.fit(X, y) 
 
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params) 
    685                 return results 
    686  
--> 687             self._run_search(evaluate_candidates) 
    688  
    689         # For multi-metric evaluation, store the best_index_, best_params_ and 
 
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates) 
   1466         evaluate_candidates(ParameterSampler( 
   1467             self.param_distributions, self.n_iter, 
-> 1468             random_state=self.random_state)) 
 
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params) 
    664                                for parameters, (train, test) 
    665                                in product(candidate_params, 
--> 666                                           cv.split(X, y, groups))) 
    667  
    668                 if len(out) < 1: 
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\parallel.py in __call__(self, iterable) 
    919             # remaining jobs. 
    920             self._iterating = False 
--> 921             if self.dispatch_one_batch(iterator): 
    922                 self._iterating = self._original_iterator is not None 
    923  
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\parallel.py in dispatch_one_batch(self, iterator) 
    757                 return False 
    758             else: 
--> 759                 self._dispatch(tasks) 
    760                 return True 
    761  
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\parallel.py in _dispatch(self, batch) 
    714         with self._lock: 
    715             job_idx = len(self._jobs) 
--> 716             job = self._backend.apply_async(batch, callback=cb) 
    717             # A job can complete so quickly than its callback is 
    718             # called before we get here, causing self._jobs to 
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\_parallel_backends.py in apply_async(self, func, callback) 
    180     def apply_async(self, func, callback=None): 
    181         """Schedule a func to be run""" 
--> 182         result = ImmediateResult(func) 
    183         if callback: 
    184             callback(result) 
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\_parallel_backends.py in __init__(self, batch) 
    547         # Don't delay the application, to avoid keeping the input 
    548         # arguments in memory 
--> 549         self.results = batch() 
    550  
    551     def get(self): 
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\parallel.py in __call__(self) 
    223         with parallel_backend(self._backend, n_jobs=self._n_jobs): 
    224             return [func(*args, **kwargs) 
--> 225                     for func, args, kwargs in self.items] 
    226  
    227     def __len__(self): 
 
C:\ProgramData\Anaconda3\lib\site-packages\joblib\parallel.py in <listcomp>(.0) 
    223         with parallel_backend(self._backend, n_jobs=self._n_jobs): 
    224             return [func(*args, **kwargs) 
--> 225                     for func, args, kwargs in self.items] 
    226  
    227     def __len__(self): 
 
C:\ProgramData\Anaconda3\lib\site-packages\sklearn\model_selection\_validation.py in _fit_and_score(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, error_score) 
    512             estimator.fit(X_train, **fit_params) 
    513         else: 
--> 514             estimator.fit(X_train, y_train, **fit_params) 
    515  
    516     except Exception as e: 
 
C:\ProgramData\Anaconda3\lib\site-packages\keras\wrappers\scikit_learn.py in fit(self, x, y, **kwargs) 
    140                 **self.filter_sk_params(self.build_fn.__call__)) 
    141         else: 
--> 142             self.model = self.build_fn(**self.filter_sk_params(self.build_fn)) 
    143  
    144         if (losses.is_categorical_crossentropy(self.model.loss) and 
 
<ipython-input-249-c3eb05e754ec> in create_model(activation, init, loss, optimizer, metrics, dropout_rate, learning_rate, decay_ratio, moment) 
     60     # Compile model ### Resets weights 
     61     opt = return_optimizer(type=optimizer, learning_rate=learning_rate) 
---> 62     model.compile(loss='mean_squared_error', optimizer=opt, metrics=['accuracy']) 
     63  
     64     return model 
 
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs) 
     93                 `optimizer`, `loss`, `metrics` or `sample_weight_mode`. 
     94         """ 
---> 95         self.optimizer = optimizers.get(optimizer) 
     96         self.loss = loss or {} 
     97         self._compile_metrics = metrics or [] 
 
C:\ProgramData\Anaconda3\lib\site-packages\keras\optimizers.py in get(identifier) 
    871     else: 
    872         raise ValueError('Could not interpret optimizer identifier: ' + 
--> 873                          str(identifier)) 
 
ValueError: Could not interpret optimizer identifier: None 

请您参考如下方法:

这可能不是最优雅的解决方案,但对我来说最明显的锤子是定义另一个返回优化器的函数。我稍微简化了你的例子。

from keras.layers import Dense 
from keras.models import Sequential 
from keras.wrappers.scikit_learn import KerasRegressor 
from sklearn.model_selection import GridSearchCV 
from keras.optimizers import Adam, SGD 
 
def return_optimizer(type, learning_rate): 
    if type == 'Adam': 
        return Adam(lr=learning_rate) 
 
    elif type == 'SGD': 
        return SGD(lr=learning_rate) 

然后,为您的 create_model() 添加一行,如下所示,

def create_model(optimizer='adam', activation = 'sigmoid',  
learning_rate=0.1): 
 
  model = Sequential() 
 
  model.add(Dense(1, activation=activation, input_shape=(1,))) 
  model.add(Dense(1, activation=activation)) 
 
  opt = return_optimizer(type=optimizer, learning_rate=learning_rate) 
  model.compile(loss='mean_squared_error', optimizer=opt, metrics=['accuracy']) 
  return model 

然后,您的 GridSerachCV() 网格是,

param_grid = { 
    'epochs': [2, 5], 
    'optimizer': ['Adam', 'SGD'], 
    'learning_rate': [0.1, 0.2] 
} 

最后,

model = KerasRegressor(build_fn=create_model, verbose=0) 
 
model_cv = GridSearchCV(estimator=model, 
                    param_grid=param_grid, 
                    n_jobs=1,    
                    cv=5 
                    ) 

请告诉我这是怎么回事。