我正在尝试使用RandomizedSearchCV优化ANN的超参数，例如一层中的神经元数量，层数，learning_rate，epoch，batch_size和dropout，代码如下：
def neural_network(num_neurons=64,num_layers=4,input_dim=8,
output_dim=2,learning_rate=1.0e-05,act='relu',
dropout=0.3):
model = Sequential()
model.add(Dense(num_neurons,activation='relu',input_dim=input_dim))
for i in range(1,num_layers):
model.add(Dense(num_neurons,activation=act))
model.add(Dropout(dropout))
model.add(Dense(output_dim,activation='softmax'))
adam = optimizers.Adam(lr=learning_rate)
model.compile(adam,
loss='categorical_crossentropy',
metrics=['accuracy']
)
return model
create_model = neural_network
model = KerasClassifier(build_fn=create_model,verbose=0)
batch_size = [16,32,64]
epochs = [200,300,500]
num_neurons = [64,128,256]
num_layers= [2,4,6]
learning_rate = [0.001, 0.01, 0.1, 0.2, 0.3]
dropout = [0.1,0.3,0.5]
param_grid = dict(batch_size=batch_size,epochs=epochs,
num_neurons=num_neurons,
num_layers=num_layers,
learning_rate=learning_rate,
dropout=dropout
)
grid = RandomizedSearchCV(estimator=model,param_distributions=param_grid,cv=3,n_iter=3)
grid_result = grid.fit(x,y,epochs=epochs,batch_size=batch_size)
我遇到的错误是：TypeError: 'list' object cannot be interpreted as an integer
任何人都可以识别代码中的问题。 谢谢
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-159-aa51f2b7cc03> in <module>
13 )
14 grid = RandomizedSearchCV(estimator=model,param_distributions=param_grid,cv=3,n_iter=3)
---> 15 grid_result = grid.fit(x,y,epochs=epochs,batch_size=batch_size)
D:\Anaconda\lib\site-packages\sklearn\model_selection\_search.py in fit(self, X, y, groups, **fit_params)
720 return results_container[0]
721
--> 722 self._run_search(evaluate_candidates)
723
724 results = results_container[0]
D:\Anaconda\lib\site-packages\sklearn\model_selection\_search.py in _run_search(self, evaluate_candidates)
1513 evaluate_candidates(ParameterSampler(
1514 self.param_distributions, self.n_iter,
-> 1515 random_state=self.random_state))
D:\Anaconda\lib\site-packages\sklearn\model_selection\_search.py in evaluate_candidates(candidate_params)
709 for parameters, (train, test)
710 in product(candidate_params,
--> 711 cv.split(X, y, groups)))
712
713 all_candidate_params.extend(candidate_params)
D:\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in __call__(self, iterable)
915 # remaining jobs.
916 self._iterating = False
--> 917 if self.dispatch_one_batch(iterator):
918 self._iterating = self._original_iterator is not None
919
D:\Anaconda\lib\site-packages\sklearn\externals\joblib\parallel.py in dispatch_one_batch(self, iterator)
757 return False
758 else:
--> 759 self._dispatch(tasks)
760 return True
761
D:\Anaconda\lib\site-packages\sklearn\externals\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
D:\Anaconda\lib\site-packages\sklearn\externals\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)
D:\Anaconda\lib\site-packages\sklearn\externals\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):
D:\Anaconda\lib\site-packages\sklearn\externals\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):
D:\Anaconda\lib\site-packages\sklearn\externals\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):
D:\Anaconda\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)
526 estimator.fit(X_train, **fit_params)
527 else:
--> 528 estimator.fit(X_train, y_train, **fit_params)
529
530 except Exception as e:
D:\Anaconda\lib\site-packages\keras\wrappers\scikit_learn.py in fit(self, x, y, sample_weight, **kwargs)
208 if sample_weight is not None:
209 kwargs['sample_weight'] = sample_weight
--> 210 return super(KerasClassifier, self).fit(x, y, **kwargs)
211
212 def predict(self, x, **kwargs):
D:\Anaconda\lib\site-packages\keras\wrappers\scikit_learn.py in fit(self, x, y, **kwargs)
150 fit_args.update(kwargs)
151
--> 152 history = self.model.fit(x, y, **fit_args)
153
154 return history
D:\Anaconda\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs)
1037 initial_epoch=initial_epoch,
1038 steps_per_epoch=steps_per_epoch,
-> 1039 validation_steps=validation_steps)
1040
1041 def evaluate(self, x=None, y=None,
D:\Anaconda\lib\site-packages\keras\engine\training_arrays.py in fit_loop(model, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch, steps_per_epoch, validation_steps)
140 indices_for_conversion_to_dense.append(i)
141
--> 142 for epoch in range(initial_epoch, epochs):
143 # Reset stateful metrics
144 for m in model.stateful_metric_functions:
TypeError: 'list' object cannot be interpreted as an integer
答案 0 :(得分：2)
问题是在下一行分别设置epochs和batch_size。
grid_result = grid.fit(x,y,epochs=epochs,batch_size=batch_size)
如下更改！我们已经在epochs中设置了batch_size和param_grid的范围。
grid_result = grid.fit(X, y)
可复制的示例：
import numpy as np
from sklearn.datasets import make_classification
from sklearn.model_selection import RandomizedSearchCV
from tensorflow.keras import Sequential
from tensorflow.keras.wrappers.scikit_learn import KerasClassifier
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras import optimizers
X, y = make_classification(n_samples=1000, n_classes=2,
n_informative=4, weights=[0.7, 0.3],
random_state=0)
def neural_network(num_neurons=64,num_layers=4,input_dim=20,
output_dim=2,learning_rate=1.0e-05,act='relu',
dropout=0.3):
model = Sequential()
model.add(Dense(num_neurons,activation='relu',input_dim=input_dim))
for i in range(1,num_layers):
model.add(Dense(num_neurons,activation=act))
model.add(Dropout(dropout))
model.add(Dense(output_dim,activation='softmax'))
adam = optimizers.Adam(lr=learning_rate)
model.compile(adam,
loss='categorical_crossentropy',
metrics=['accuracy']
)
return model
model = KerasClassifier(build_fn=neural_network,verbose=0)
batch_size = [16,32,64]
epochs = [2,3 ]
num_neurons = [6,1,2]
num_layers= [1,2]
learning_rate = [0.001, 0.01, 0.1, 0.2, 0.3]
dropout = [0.1,0.3,0.5]
param_grid = dict(batch_size=batch_size,epochs=epochs,
num_neurons=num_neurons,
num_layers=num_layers,
learning_rate=learning_rate,
dropout=dropout
)
grid = RandomizedSearchCV(estimator=model,param_distributions=param_grid,cv=2,n_iter=1)
grid_result = grid.fit(X, y)
grid_result.best_params_
输出：
{'batch_size': 64,
'dropout': 0.1,
'epochs': 2,
'learning_rate': 0.01,
'num_layers': 1,
'num_neurons': 6}