1

我正在尝试解决超参数调整情况下的错误:

我正在尝试处理的图像具有(64, 64, 3)(宽度、高度、通道)的形状。(64, 64, 1)由于我正在执行二进制分类任务,因此相应的标签具有形状,但对于每个像素。

我使用的模型是 UNET 模型:

def make_model(dropout_c1, dropout_c2, dropout_c3, dropout_c4,   
               dropout_c5, final_activation, optimizer='Adam'):

    inputs = Input((64, 64, 3))
    s = Lambda(lambda x: x / 255) (inputs)

    c1 = Conv2D(64, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (s)
    c1 = Dropout(dropout_c1) (c1)
    c1 = Conv2D(16, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (c1)
    p1 = MaxPooling2D((2, 2)) (c1)

    c2 = Conv2D(32, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (p1)
    c2 = Dropout(dropout_c2) (c2)
    c2 = Conv2D(32, (3, 3), activation='relu',
                     kernel_initializer='he_normal', padding='same') (c2)
    p2 = MaxPooling2D((2, 2)) (c2)

    c3 = Conv2D(64, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (p2)
    c3 = Dropout(dropout_c3) (c3)
    c3 = Conv2D(64, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (c3)
    p3 = MaxPooling2D((2, 2)) (c3)

    c4 = Conv2D(128, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (p3)
    c4 = Dropout(dropout_c4) (c4)
    c4 = Conv2D(128, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (c4)
    p4 = MaxPooling2D(pool_size=(2, 2)) (c4)

    c5 = Conv2D(256, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (p4)
    c5 = Dropout(dropout_c5) (c5)
    c5 = Conv2D(256, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (c5)

    u6 = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same') (c5)
    u6 = concatenate([u6, c4])
    c6 = Conv2D(128, (3, 3), activation='relu',  
                kernel_initializer='he_normal', padding='same') (u6)
    c6 = Dropout(dropout_c4) (c6)
    c6 = Conv2D(128, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (c6)

    u7 = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same') (c6)
    u7 = concatenate([u7, c3])
    c7 = Conv2D(64, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (u7)
    c7 = Dropout(dropout_c3) (c7)
    c7 = Conv2D(64, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (c7)

    u8 = Conv2DTranspose(32, (2, 2), strides=(2, 2), padding='same') (c7)
    u8 = concatenate([u8, c2])
    c8 = Conv2D(32, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (u8)
    c8 = Dropout(dropout_c2) (c8)
    c8 = Conv2D(32, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (c8)

    u9 = Conv2DTranspose(16, (2, 2), strides=(2, 2), padding='same') (c8)
    u9 = concatenate([u9, c1], axis=3)
    c9 = Conv2D(16, (3, 3), activation='relu',
                kernel_initializer='he_normal', padding='same') (u9)
    c9 = Dropout(dropout_c1) (c9)
    c9 = Conv2D(16, (3, 3), activation='relu', 
                kernel_initializer='he_normal', padding='same') (c9)

    outputs = Conv2D(1, (1, 1), activation=final_activation) (c9)
    model = Model(inputs=[inputs], outputs=[outputs])

    model.compile(optimizer=optimizer, loss='binary_crossentropy', 
                  metrics=['accuracy'])
    model.summary()

    return model

输出:

print(np.shape(X_train)) 
print(np.shape(y_train))

是:

(65792, 64, 64, 3)
(65792, 64, 64, 1)

-

cnn_model = KerasClassifier(build_fn=make_model)
batch_size_ = [64, 128, 256]

dropout_c1_ = [0.1, 0.3]
dropout_c2_ = [0.1, 0.3]
dropout_c3_ = [0.1, 0.3]
dropout_c4_ = [0.1, 0.3]
dropout_c5_ = [0.1, 0.3]

optimizer_ = ['Adam', 'RMSprop', 'Adagrad', 'SGD']
final_activation_ = ['sigmoid', 'softmax']

param_grid={'optimizer' : optimizer_,
            'dropout_c1': dropout_c1_,
            'dropout_c2': dropout_c2_,
            'dropout_c3': dropout_c3_,
            'dropout_c4': dropout_c4_,
            'dropout_c5': dropout_c5_,
             'final_activation': final_activation_,
             'epochs': [30],
             'batch_size': batch_size_
              }
filepath = "best_cnn.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='acc', verbose=1,
                             save_best_only=True, mode='max')

grid = GridSearchCV(cnn_model, param_grid, cv=2, 
                    scoring='average_precision', n_jobs=1, verbose=1)

来电:

grid_result = grid.fit(X_train, y_train, callbacks=[checkpoint])

将导致以下错误:

Fitting 2 folds for each of 768 candidates, totalling 1536 fits

[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-49-b1fdcdb4a9af> in <module>
----> 1 grid_result = grid.fit(X_train, y_train, callbacks=[checkpoint])

~/venv/lib/python3.6/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]

~/venv/lib/python3.6/site-packages/sklearn/model_selection/_search.py in _run_search(self, evaluate_candidates)
   1189     def _run_search(self, evaluate_candidates):
   1190         """Search all candidates in param_grid"""
-> 1191         evaluate_candidates(ParameterGrid(self.param_grid))
   1192 
   1193 

~/venv/lib/python3.6/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)

~/venv/lib/python3.6/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 

~/venv/lib/python3.6/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 

~/venv/lib/python3.6/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

~/venv/lib/python3.6/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)

~/venv/lib/python3.6/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):

~/venv/lib/python3.6/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):

~/venv/lib/python3.6/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):

~/venv/lib/python3.6/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:

~/venv/lib/python3.6/site-packages/keras/wrappers/scikit_learn.py in fit(self, x, y, sample_weight, **kwargs)
    204             y = np.searchsorted(self.classes_, y)
    205         else:
--> 206             raise ValueError('Invalid shape for y: ' + str(y.shape))
    207         self.n_classes_ = len(self.classes_)
    208         if sample_weight is not None:

ValueError: Invalid shape for y: (32896, 64, 64, 1)
4

0 回答 0