CNN Keras 使用 Hyperas 错误：AttributeError: 'str' object has no attribute 'ndim'

Question

模型编译并运行，直到到达代码末尾评估模型的行。我认为错误在于它收到了一个字符串，但没想到会收到一个字符串，但我不知道如何修复它。提前致谢。

def data():

train_data_dir = '/home/bjorn/Downloads/CATS_DOGS2/train'
validation_data_dir = '/home/bjorn/Downloads/CATS_DOGS2/test'
return train_data_dir, validation_data_dir


def model_one(train_data_dir, validation_data_dir):

img_width, img_height = 150, 150

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()

model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 input_shape=input_shape, activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(Conv2D({{choice([32, 64, 128, 256])}}, 3, 3, border_mode='same',
                 activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense({{choice([32, 64, 128, 256, 512])}},
                activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(Dropout({{uniform(0, 0.75)}}))

model.add(Dense({{choice([32, 64, 128, 256, 512])}},
                activation={{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))
model.add(Dropout({{uniform(0, 0.75)}}))

model.add(Dense(1))
model.add(Activation({{choice(['relu', 'sigmoid', 'softmax', 'tanh'])}}))

model.compile(loss='binary_crossentropy',
              optimizer={{choice(['rmsprop', 'adam', 'sgd'])}},
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.1,
    zoom_range=0.1,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=16,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=16,
    class_mode='binary')

result = model.fit_generator(
    train_generator,
    steps_per_epoch=125,
    epochs=5,
    verbose=2,
    validation_data=validation_generator,
    validation_steps=50)

# get the highest validation accuracy of the training epochs
validation_acc = np.amax(result.history['val_acc'])
print('Best validation acc of epoch:', validation_acc)
return {'loss': -validation_acc, 'status': STATUS_OK, 'model': model}

if __name__ == '__main__':
    best_run, best_model = optim.minimize(model=model_one,
                                          data=data,
                                          algo=tpe.suggest,
                                          max_evals=10,
                                          trials=Trials())

train_data_dir, validation_data_dir = data()
print('Evaluation of best performing model:')
print(best_model.evaluate(validation_data_dir))
print('Best performing model chosen hyper-parameters:')
print(best_run)

最佳性能模型的评估： data = [standardize_single_array(x) for x in data] 文件“/home/bjorn/PycharmProjects/Test/venv/lib/python3.5/site-packages/keras/engine/training_utils.py”，第 92 行，在 data = [standardize_single_array(x) for x in data] 文件“/home/bjorn/PycharmProjects/Test/venv/lib/python3.5/site-packages/keras/engine/training_utils.py”，第 27 行，位于standardize_single_array elif x.ndim == 1： AttributeError: 'str' 对象没有属性 'ndim'

进程以退出代码 1 结束

Answer 1

我从未使用过 keras，但据我所知， 很明显 best_model.evaluate(arg) 函数需要一个 numpy 数组作为参数。