ValueError：無法處理多標記指示符和二進制混合使用GridSearchCV和KerasClassifier問題

Question

我有MNIST數據的CNN代碼，它將數據集分成訓練集和測試集，僅用於2和7。運行該代碼時，它在測試集上提供了約98％的準確度。

因此，爲了提高準確度，我嘗試使用keras.wrappers.scikit_learn中的KerasClassifier。在GridSearchCV中使用分類器我想要找到最佳參數，但是在運行代碼時第一次迭代一切正常，但是從下一次迭代中引發錯誤。

下面是代碼：

# This is the normal CNN model without GridSearch 
from __future__ import print_function 
import keras 
from keras.datasets import mnist 
from keras.models import Sequential 
from keras.layers import Dense, Dropout, Flatten 
from keras.layers import Conv2D, MaxPooling2D 
from keras import backend as K 
import numpy as np 
batch_size = 128 
num_classes = 2 
epochs = 12 
# input image dimensions 
img_rows, img_cols = 28, 28 

# the data, shuffled and split between train and test sets 
(x_train, y_train), (x_test, y_test) = mnist.load_data() 

#Only look at 3s and 8s 
train_picks = np.logical_or(y_train==2,y_train==7) 
test_picks = np.logical_or(y_test==2,y_test==7) 

x_train = x_train[train_picks] 
x_test = x_test[test_picks] 
y_train = np.array(y_train[train_picks]==7,dtype=int) 
y_test = np.array(y_test[test_picks]==7,dtype=int) 


if K.image_data_format() == 'channels_first': 
    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols) 
    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols) 
    input_shape = (1, img_rows, img_cols) 
else: 
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1) 
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1) 
    input_shape = (img_rows, img_cols, 1) 

x_train = x_train.astype('float32') 
x_test = x_test.astype('float32') 
x_train /= 255 
x_test /= 255 
print('x_train shape:', x_train.shape) 
print(x_train.shape[0], 'train samples') 
print(x_test.shape[0], 'test samples') 

# convert class vectors to binary class matrices 
y_train = keras.utils.to_categorical(y_train, num_classes) 
y_test = keras.utils.to_categorical(y_test, num_classes) 

model = Sequential() 
model.add(Conv2D(4, kernel_size=(3, 3),activation='relu',input_shape=input_shape)) 
model.add(Conv2D(8, (3, 3), activation='relu')) 
model.add(MaxPooling2D(pool_size=(2, 2))) 
model.add(Dropout(0.25)) 
model.add(Flatten()) 
model.add(Dense(16, activation='relu')) 
model.add(Dropout(0.5)) 
model.add(Dense(2, activation='softmax')) 

model.compile(loss=keras.losses.categorical_crossentropy, 
       optimizer=keras.optimizers.Adadelta(), 
       metrics=['accuracy']) 

model.fit(x_train, y_train, 
      batch_size=batch_size, 
      epochs=epochs, 
      verbose=1, 
      validation_data=(x_test, y_test)) 
score = model.evaluate(x_test, y_test, verbose=0) 
print('Test loss:', score[0]) 
print('Test accuracy:', score[1]) 

# Improving the accuracy using GridSearch 
from keras.wrappers.scikit_learn import KerasClassifier 
from sklearn.model_selection import GridSearchCV 
from keras.models import Sequential 
from keras.layers import Dense 
def build_model(optimizer): 
    print(optimizer,batch_size,epochs) 
    model = Sequential() 
    model.add(Conv2D(4, kernel_size=(3, 3),activation='relu',input_shape=input_shape)) 
    model.add(Conv2D(8, (3, 3), activation='relu')) 
    model.add(MaxPooling2D(pool_size=(2, 2))) 
    model.add(Dropout(0.25)) 
    model.add(Flatten()) 
    model.add(Dense(16, activation='relu')) 
    model.add(Dropout(0.5)) 
    model.add(Dense(2, activation='softmax')) 

    model.compile(loss=keras.losses.categorical_crossentropy, 
        optimizer=optimizer, 
        metrics=['accuracy']) 
    return model 
model = KerasClassifier(build_fn = build_model) 
parameters = {'batch_size': [128, 256], 
       'epochs': [10, 20], 
       'optimizer': ['rmsprop']} 
grid_search = GridSearchCV(estimator = model, 
          param_grid = parameters, 
          scoring = 'accuracy', 
          cv = 10) 
grid_search = grid_search.fit(x_train, y_train) 
best_parameters = grid_search.best_params_ 
best_accuracy = grid_search.best_score_ 

這是代碼的輸出：

rmsprop 128 12 
Epoch 1/10 
11000/11000 [==============================] - 3s - loss: 0.1654 - acc: 0.9476  
Epoch 2/10 
11000/11000 [==============================] - 3s - loss: 0.0699 - acc: 0.9786  
Epoch 3/10 
11000/11000 [==============================] - 2s - loss: 0.0557 - acc: 0.9839  
Epoch 4/10 
11000/11000 [==============================] - 2s - loss: 0.0510 - acc: 0.9839  
Epoch 5/10 
11000/11000 [==============================] - 2s - loss: 0.0471 - acc: 0.9853  
Epoch 6/10 
11000/11000 [==============================] - 2s - loss: 0.0417 - acc: 0.9875  
Epoch 7/10 
11000/11000 [==============================] - 2s - loss: 0.0399 - acc: 0.9870  
Epoch 8/10 
11000/11000 [==============================] - 2s - loss: 0.0365 - acc: 0.9885  
Epoch 9/10 
11000/11000 [==============================] - 2s - loss: 0.0342 - acc: 0.9899  
Epoch 10/10 
11000/11000 [==============================] - 2s - loss: 0.0321 - acc: 0.9903  
768/1223 [=================>............] - ETA: 0sTraceback (most recent call last): 

    File "<ipython-input-4-975b20661114>", line 30, in <module> 
    grid_search = grid_search.fit(x_train, y_train) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 945, in fit 
    return self._fit(X, y, groups, ParameterGrid(self.param_grid)) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_search.py", line 564, in _fit 
    for parameters in parameter_iterable 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 758, in __call__ 
    while self.dispatch_one_batch(iterator): 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 608, in dispatch_one_batch 
    self._dispatch(tasks) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 571, in _dispatch 
    job = self._backend.apply_async(batch, callback=cb) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 109, in apply_async 
    result = ImmediateResult(func) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/_parallel_backends.py", line 326, in __init__ 
    self.results = batch() 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in __call__ 
    return [func(*args, **kwargs) for func, args, kwargs in self.items] 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/externals/joblib/parallel.py", line 131, in <listcomp> 
    return [func(*args, **kwargs) for func, args, kwargs in self.items] 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 260, in _fit_and_score 
    test_score = _score(estimator, X_test, y_test, scorer) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/model_selection/_validation.py", line 288, in _score 
    score = scorer(estimator, X_test, y_test) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/metrics/scorer.py", line 98, in __call__ 
    **self._kwargs) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 172, in accuracy_score 
    y_type, y_true, y_pred = _check_targets(y_true, y_pred) 

    File "/home/thakkar_/anaconda3/lib/python3.6/site-packages/sklearn/metrics/classification.py", line 82, in _check_targets 
    "".format(type_true, type_pred)) 

ValueError: Can't handle mix of multilabel-indicator and binary 

請幫幫忙！

Answer 1

的誤差似乎是在你解析字典參數的方式..

here從一個例子：

import numpy 
from sklearn.model_selection import GridSearchCV 
from keras.models import Sequential 
from keras.layers import Dense 
from keras.wrappers.scikit_learn import KerasClassifier 
from keras.optimizers import SGD 
# Function to create model, required for KerasClassifier 
def create_model(learn_rate=0.01, momentum=0): 
    # create model 
    model = Sequential() 
    model.add(Dense(12, input_dim=8, activation='relu')) 
    model.add(Dense(1, activation='sigmoid')) 
    # Compile model 
    optimizer = SGD(lr=learn_rate, momentum=momentum) 
    model.compile(loss='binary_crossentropy', optimizer=optimizer, metrics=['accuracy']) 
    return model 
# fix random seed for reproducibility 
seed = 7 
numpy.random.seed(seed) 
# load dataset 
dataset = numpy.loadtxt("pima-indians-diabetes.csv", delimiter=",") 
# split into input (X) and output (Y) variables 
X = dataset[:,0:8] 
Y = dataset[:,8] 
# create model 
model = KerasClassifier(build_fn=create_model, epochs=100, batch_size=10, verbose=0) 
# define the grid search parameters 
learn_rate = [0.001, 0.01, 0.1, 0.2, 0.3] 
momentum = [0.0, 0.2, 0.4, 0.6, 0.8, 0.9] 
param_grid = dict(learn_rate=learn_rate, momentum=momentum) 
grid = GridSearchCV(estimator=model, param_grid=param_grid, n_jobs=-1) 
grid_result = grid.fit(X, Y) 
# summarize results 
print("Best: %f using %s" % (grid_result.best_score_, grid_result.best_params_)) 
means = grid_result.cv_results_['mean_test_score'] 
stds = grid_result.cv_results_['std_test_score'] 
params = grid_result.cv_results_['params'] 
for mean, stdev, param in zip(means, stds, params): 
    print("%f (%f) with: %r" % (mean, stdev, param)) 

GridseachCV基本上採用元件從與它的輸入參數相匹配的字典，並且訓練它。您解析完整的詞典，但batch_size和epochs不會在函數中參數...

# Improving the accuracy using GridSearch 
from keras.wrappers.scikit_learn import KerasClassifier 
from sklearn.model_selection import GridSearchCV 
from keras.models import Sequential 
from keras.layers import Dense 
def build_model(optimizer = 'adam'): 
    model = Sequential() 
    model.add(Conv2D(4, kernel_size=(3, 3),activation='relu',input_shape=input_shape)) 
    model.add(Conv2D(8, (3, 3), activation='relu')) 
    model.add(MaxPooling2D(pool_size=(2, 2))) 
    model.add(Dropout(0.25)) 
    model.add(Flatten()) 
    model.add(Dense(16, activation='relu')) 
    model.add(Dropout(0.5)) 
    model.add(Dense(2, activation='softmax')) 

    model.compile(loss=keras.losses.categorical_crossentropy, 
        optimizer=optimizer, 
        metrics=['accuracy']) 
    return model 
model = KerasClassifier(build_fn = build_model) 
parameters = {'batch_size': [128, 256], 
       'epochs': [10, 20], 
       'optimizer': ['rmsprop']} 
grid_search = GridSearchCV(estimator = model, 
          param_grid = parameters, 
          scoring = 'accuracy', 
          cv = 10) 
grid_search = grid_search.fit(x_train, y_train) 
best_parameters = grid_search.best_params_ 
best_accuracy = grid_search.best_score_ 

也許像這樣的工作..沒有測試它。