ValueError：检查目标时出错：预期density_20的形状为（23，），但数组的形状为（1，）

Question

我收到此错误消息：ValueError：检查目标时出错：预期density_20具有形状（23，）但具有形状（1，）的数组。我是深度学习的初学者，找不到解决方案。

datagen = ImageDataGenerator(rescale=1./255)
batch_size = 20

def extract_features(directory, sample_count):
    try:

        features = np.zeros(shape=(sample_count, 7, 7, 1280))
        labels = np.zeros(shape=(sample_count))
        generator = datagen.flow_from_directory(
            directory,
            target_size=(224, 224),
            batch_size=batch_size,
            class_mode='binary')
        i = 0
        for inputs_batch, labels_batch in generator:
            features_batch = conv_base.predict(inputs_batch)
            features[i * batch_size : (i + 1) * batch_size] = features_batch
            labels[i * batch_size : (i + 1) * batch_size] = labels_batch
            i += 1
            if i * batch_size >= sample_count:

                break

    except OSError as e:
        pass

    return features, labels

train_features, train_labels = extract_features(train_dir, 2000)
validation_features, validation_labels = extract_features(validation_dir, 1000)
test_features, test_labels = extract_features(test_dir, 1000)

train_features = np.reshape(train_features, (2000, 7 * 7 * 1280))
validation_features = np.reshape(validation_features, (1000, 7 * 7 * 1280))
test_features = np.reshape(test_features, (1000, 7 * 7 * 1280))

from keras import models
from keras import layers
from keras import optimizers

model = models.Sequential()
model.add(layers.Dense(256, activation='relu', input_dim=7 * 7 * 1280))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(23, activation='sigmoid'))

model.compile(optimizer='rmsprop',
              loss='binary_crossentropy',
              metrics=['acc'])

history = model.fit(train_features, train_labels,
                    epochs=100,
                    batch_size=30,
                    validation_data=(validation_features, validation_labels))

我遇到多标签问题。我的神经网络应该能够区分23种不同的类别。我在文献中找到了解决该问题的一些方法。这就是我的代码产生的方式。 也许有人可以帮助我。

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-18-d4f0dfbf741a> in <module>()
     15                     epochs=100,
     16                     batch_size=30,
---> 17                     validation_data=(validation_features, validation_labels))

/usr/local/lib/python3.5/dist-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)
    950             sample_weight=sample_weight,
    951             class_weight=class_weight,
--> 952             batch_size=batch_size)
    953         # Prepare validation data.
    954         do_validation = False

/usr/local/lib/python3.5/dist-packages/keras/engine/training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_array_lengths, batch_size)
    787                 feed_output_shapes,
    788                 check_batch_axis=False,  # Don't enforce the batch size.
--> 789                 exception_prefix='target')
    790 
    791             # Generate sample-wise weight values given the `sample_weight` and

/usr/local/lib/python3.5/dist-packages/keras/engine/training_utils.py in standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
    136                             ': expected ' + names[i] + ' to have shape ' +
    137                             str(shape) + ' but got array with shape ' +
--> 138                             str(data_shape))
    139     return data
    140 

ValueError: Error when checking target: expected dense_20 to have shape (23,) but got array with shape (1,)