python - CNN 给出有偏见的结果

Question

我在 CNN 上使用二元分类器。我有两个类别“我”和“其他”。我有大约 250 张我自己的图像和 500 张其他人的图像(随机面孔数据库)。我目前的图层实现非常简单

    self.model.add(Conv2D(128, (2, 2), padding='same', 
    input_shape=dataset.X_train.shape[1:]))
    self.model.add(Activation('relu'))
    self.model.add(MaxPooling2D(pool_size=(2, 2)))
    self.model.add(Dropout(0.25))

    self.model.add(Conv2D(64, (2, 2), padding='same'))
    self.model.add(Activation('relu'))
    self.model.add(MaxPooling2D(pool_size=(2, 2)))
    self.model.add(Dropout(0.25))

    self.model.add(Conv2D(32, (1, 1), padding='same'))
    self.model.add(Activation('relu'))
    self.model.add(MaxPooling2D(pool_size=(2, 2)))
    self.model.add(Dropout(0.5))
    self.model.add(Dense(512))
    self.model.add(Activation('relu'))
    self.model.add(Dropout(0.25))
    self.model.add(Dense(2)) # for two classes
    self.model.add(Activation('softmax'))

我的网络准确率达到 93%

我的问题是，当我使用这个网络预测人脸时，它总是将任何人脸识别为我的。我裁剪了脸部，应用了 gabor 过滤器，但没有任何效果。任何建议将不胜感激。

随机人脸预测结果:【KK代表我的脸】概率总是超过 97%:

KK identified!
1/1 [==============================] - 0s
[[ 0.9741978  0.0258022]]
1/1 [==============================] - 0s

KK identified!
1/1 [==============================] - 0s
[[ 0.9897241   0.01027592]]
1/1 [==============================] - 0s

我的图像预测结果:[KK 代表我的脸]概率总是超过 99%:

KK identified!
1/1 [==============================] - 0s
[[ 0.99639165  0.00360837]]
1/1 [==============================] - 0s
KK identified!
1/1 [==============================] - 0s
[[ 0.99527925  0.00472075]]
1/1 [==============================] - 0s

训练代码

   def get_data(self, img_rows=IMAGE_SIZE, img_cols=IMAGE_SIZE, img_channels=3, nb_classes=2):

        images, labels = fetch_data('./data/')
        labels = np.reshape(labels, [-1])

        X_train, X_test, y_train, y_test =  \
            train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100))
        X_valid, X_test, y_valid, y_test = \
            train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100))
            #train_test_split(images, labels, test_size=0.3, random_state=np.random.seed(15))

        if K.image_dim_ordering() == 'th':
            X_train = X_train.reshape(X_train.shape[0], 3, img_rows, img_cols)
            X_valid = X_valid.reshape(X_valid.shape[0], 3, img_rows, img_cols)
            X_test = X_test.reshape(X_test.shape[0], 3, img_rows, img_cols)
            # input_shape = (3, img_rows, img_cols)
        else:
            X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 3)
            X_valid = X_valid.reshape(X_valid.shape[0], img_rows, img_cols, 3)
            X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 3)
            # input_shape = (img_rows, img_cols, 3)

        Y_train = np_utils.to_categorical(y_train, nb_classes)
        Y_valid = np_utils.to_categorical(y_valid, nb_classes)
        Y_test = np_utils.to_categorical(y_test, nb_classes)

        X_train = X_train.astype('float32')
        X_valid = X_valid.astype('float32')
        X_test = X_test.astype('float32')
        X_train /= 255
        X_valid /= 255
        X_test /= 255

        self.X_train = X_train
        self.X_valid = X_valid
        self.X_test = X_test
        self.Y_train = Y_train
        self.Y_valid = Y_valid
        self.Y_test = Y_test



def train_network(self, dataset, batch_size=32, nb_epoch=40, data_augmentation=True):
    sgd = SGD(lr=0.003, decay=0.0000001, momentum=0.9, nesterov=True)

    # adam = Adam(lr=0.01, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0001)
    self.model.compile(loss='binary_crossentropy',
                       optimizer=sgd,
                       metrics=['accuracy'])
    if not data_augmentation:
        processed_data = self.model.fit(dataset.X_train, dataset.Y_train,
                       batch_size=batch_size,
                       nb_epoch=nb_epoch,
                       validation_data=(dataset.X_valid, dataset.Y_valid),
                       shuffle=True)
    else:
        datagenerator = ImageDataGenerator(
            featurewise_center=False,
            samplewise_center=False,
            featurewise_std_normalization=False,
            samplewise_std_normalization=False,
            zca_whitening=False,
            rotation_range=20,
            width_shift_range=0.2,
            height_shift_range=0.2,
            horizontal_flip=True,
            vertical_flip=False)

        datagenerator.fit(dataset.X_train)

        processed_data = self.model.fit_generator(datagen.flow(dataset.X_train, dataset.Y_train, batch_size=batch_size, shuffle=True),
                                 samples_per_epoch=dataset.X_train.shape[0], nb_epoch=nb_epoch, validation_data=(dataset.X_valid, dataset.Y_valid))

谢谢

[更新:6 月 11 日]

图层

def build_model(self, dataset, nb_classes=2):
        self.model = Sequential()

        self.model.add(Conv2D(32, (3, 3), padding='same', input_shape=dataset.X_train.shape[1:]))
        self.model.add(Activation('relu'))
        self.model.add(Conv2D(32, (3, 3)))
        self.model.add(Activation('relu'))
        self.model.add(MaxPooling2D(pool_size=(2, 2)))
        self.model.add(Dropout(0.5))

        self.model.add(Conv2D(16, (3, 3), padding='same'))
        self.model.add(Activation('relu'))
        self.model.add(Conv2D(16, (3, 3)))
        self.model.add(Activation('relu'))
        self.model.add(MaxPooling2D(pool_size=(2, 2)))
        self.model.add(Dropout(0.5))

        self.model.add(Flatten())
        self.model.add(Dense(512))
        self.model.add(Activation('relu'))
        self.model.add(Dropout(0.5))
        self.model.add(Dense(nb_classes))
        self.model.add(Activation('softmax'))

        self.model.summary()

数据扩充

    # this will do preprocessing and realtime data augmentation
    datagen = ImageDataGenerator(
        featurewise_center=True,             # set input mean to 0 over the dataset
        samplewise_center=False,              # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,   # divide each input by its std
        zca_whitening=False,                  # apply ZCA whitening
        rotation_range=20,                     # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=0.2,                # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.2,               # randomly shift images vertically (fraction of total height)
        # rescale=1. / 255,
        # shear_range=0.2,
        # zoom_range=0.2,
        horizontal_flip=True,                 # randomly flip images
        vertical_flip=False)                  # randomly flip images

    datagen.fit(dataset.X_train)

    checkpoint = ModelCheckpoint(self.FILE_PATH, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
    callback_list = [checkpoint]

    # fit the model on the batches generated by datagen.flow()
    train_generator = datagen.flow(dataset.X_train, dataset.Y_train, batch_size=batch_size, shuffle=True)

    history = self.model.fit_generator(train_generator,
                                       samples_per_epoch=dataset.X_train.shape[0],
                                       nb_epoch=nb_epoch,
                                       validation_data=(dataset.X_valid, dataset.Y_valid),
                                       callbacks=callback_list)

数据集

class DataSet(object):

    def __init__(self):
        self.X_train = None
        self.X_valid = None
        self.X_test = None
        self.Y_train = None
        self.Y_valid = None
        self.Y_test = None

    # support only binary classification for now, thus 2 class limit
    def get_data(self, img_rows=IMAGE_SIZE, img_cols=IMAGE_SIZE, img_channels=3, nb_classes=2):

        images, labels = fetch_data('./data/')
        labels = np.reshape(labels, [-1])

        X_train, X_test, y_train, y_test =  \
            train_test_split(images, labels, test_size=0.2, random_state=random.randint(0, 100))

        X_valid, X_test, y_valid, y_test = \
            train_test_split(images, labels, test_size=0.2, random_state=random.randint(0, 100))

        if K.image_dim_ordering() == 'th':
            X_train = X_train.reshape(X_train.shape[0], 3, img_rows, img_cols)
            X_valid = X_valid.reshape(X_valid.shape[0], 3, img_rows, img_cols)
            X_test = X_test.reshape(X_test.shape[0], 3, img_rows, img_cols)

        else:
            X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 3)
            X_valid = X_valid.reshape(X_valid.shape[0], img_rows, img_cols, 3)
            X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 3)


        # convert class vectors to binary class matrices
        Y_train = np_utils.to_categorical(y_train, nb_classes)
        Y_valid = np_utils.to_categorical(y_valid, nb_classes)
        Y_test = np_utils.to_categorical(y_test, nb_classes)

        X_train = X_train.astype('float32')
        X_valid = X_valid.astype('float32')
        X_test = X_test.astype('float32')
        X_train /= 255
        X_valid /= 255
        X_test /= 255

        self.X_train = X_train
        self.X_valid = X_valid
        self.X_test = X_test
        self.Y_train = Y_train
        self.Y_valid = Y_valid
        self.Y_test = Y_test

Answer 1

结果一点也不奇怪。网络从未了解是什么让你的脸与众不同，而只是记住是什么让 500 集与你的不同。一旦你呈现一张新面孔，它就没有它的“内存”，因此将它解释为你的，只是因为 500 张面孔中存在的特征都没有出现在第 501 张面孔中。

解决这个问题的一些想法:

• 使用 ImageDataGenerator 扩充您的数据，正如 petezurich 所提议的那样。
• 增加内核大小。 2*2 太小，无法捕捉面部特征。考虑3*3，甚至在第一个隐藏层堆叠两个3*3。
• 考虑使用批量归一化和正则化。将 Dropout 增加到 0.5。
• 考虑用 diluted convolutions 替换池化层(在 Keras 中可用)。
• 确保规范化输入数据。
• 减少第一层中特征映射(过滤器)的数量。考虑使用例如32 个 3*3 map 而不是 128 个微小元素(如果我猜的话，这些是你的主要问题)。通过这种方式，您将迫使网络进行概括，而不是学习一些细微差别。

对我最后一点的假设的一个很好的测试是可视化隐藏层中的激活，尤其是第一个隐藏层。我有一种感觉，你的网络会激活一些不相关的特征(或者更确切地说 - 噪音)，而不是“人类特征”(比如眼睛、发型)。

[添加更多代码后进行编辑]

• 将您的输入数据以零为中心。
• 降低批量大小。由于样本太少，您不希望在一个批处理中进行太多平均。

我仍然认为使用例如第一个隐藏层中的 16 或 32 个过滤器应该是第一个要检查的东西。看看你的脸。你能找出 128 个“特征”吗？除非你有一些严重的粉刺，否则我不这么认为。