python - 使用 keras 中的 grid_search 和 flow_from_directory 进行 super 参数优化

Question

我尝试优化用于图像分类的 keras CNN 中的超参数。我决定使用 sklearn 的网格搜索。我克服了从 keras flow_from_directory 中制作 x 和 y 的基本困难，但它仍然不起作用。最后一行错误ValueError:dropout不是合法参数

def grid_model(optimizer='adam',
                     kernel_initializer='random_uniform', 
                     dropout=0.2,
                    loss='categorical_crossentropy'):

    model = Sequential()

    model.add(Conv2D(6,(5,5),activation="relu",padding="same",
                     input_shape=(img_width, img_height, 3)))
    model.add(MaxPooling2D((2,2)))
    model.add(Dropout(dropout))

    model.add(Conv2D(16,(5,5),activation="relu"))
    model.add(MaxPooling2D((2,2)))
    model.add(Dropout(dropout))

    model.add(Flatten())

    model.add(Dense(120, activation='relu', kernel_initializer=kernel_initializer))
    model.add(Dropout(dropout))
    model.add(Dense(84, activation='relu', kernel_initializer=kernel_initializer))
    model.add(Dropout(dropout))
    model.add(Dense(10, activation='softmax'))

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

train_generator = ImageDataGenerator(rescale=1/255)

validation_generator = ImageDataGenerator(rescale=1/255)

# Retrieve images and their classes for train and validation sets
train_flow = train_generator.flow_from_directory(directory=train_data_dir, 
                                                 batch_size=batch_size, 
                                                 target_size=(img_height,img_width))

validation_flow = validation_generator.flow_from_directory(directory=validation_data_dir, 
                                                           batch_size=batch_size,
                                                           target_size=(img_height,img_width),
                                                            shuffle = False)

clf = KerasClassifier(build_fn=grid_model(), epochs=epochs, verbose=0)

param_grid = {
    'clf__optimizer':['adam', 'Nadam'],
    'clf__epochs':[100, 200],
    'clf__dropout':[0.1, 0.2, 0.5],
    'clf__kernel_initializer':['normal','uniform'],
    'clf__loss':['categorical_crossentropy', 
                     'sparse_categorical_crossentropy', 
                     'kullback_leibler_divergence']
}

pipeline = Pipeline([('clf',clf)])

(X_train, Y_train) = train_flow.next()

grid = GridSearchCV(pipeline, cv=2, param_grid=param_grid)
grid.fit(X_train, Y_train)

Answer 1

问题出在这一行:

clf = KerasClassifier(build_fn=grid_model(), epochs=epochs, verbose=0)

修改为

clf = KerasClassifier(build_fn=grid_model, epochs=epochs, verbose=0)

不应调用 grid_model 方法，但应传递对其的引用。

此外，在损失列表中，不能使用“sparse_categorical_crossentropy”(整数)，因为模型所需的输出形状与“categorical_crossentropy”(one-hot)的输出形状不兼容。