淘先锋技术网

首页 1 2 3 4 5 6 7

使用两种方法构建模型,一种是如下所示方法,构建一个VGG16网络:

    model = Sequential()

    model.add(Conv2D(32, (3, 3), strides=(1, 1), input_shape=(299, 299, 3), padding='same', activation='relu',
                     kernel_initializer='uniform'))
    model.add(Conv2D(32, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(64, (3, 2), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(64, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu', kernel_initializer='uniform'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Flatten())
    model.add(Dense(2048, activation='relu'))
    model.add(Dropout(0.25))
    model.add(Dense(2048, activation='relu'))
    model.add(Dropout(0.25))
    model.add(Dense(100, activation='softmax'))

    sgd = SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True)
    model.compile(optimizer=sgd, loss='categorical_crossentropy', metrics=['accuracy'])

    model.load_weights('c:/wei.h5')
    classes = model.predict_classes(x_test)[0]
    classlist = model.predict_proba(x_test).tolist()  # 获取每个类的概率

或者使用如下方法,构建一个inception_v4网络:

CONV_BLOCK_COUNT = 0  # 用来命名计数卷积编号
INCEPTION_A_COUNT = 0
INCEPTION_B_COUNT = 0
INCEPTION_C_COUNT = 0


def conv_block(x, nb_filters, nb_row, nb_col, strides=(1, 1), padding='same', use_bias=False):
    global CONV_BLOCK_COUNT
    CONV_BLOCK_COUNT += 1
    with K.name_scope('conv_block_' + str(CONV_BLOCK_COUNT)):
        x = Conv2D(filters=nb_filters,
                   kernel_size=(nb_row, nb_col),
                   strides=strides,
                   padding=padding,
                   use_bias=use_bias)(x)
        x = BatchNormalization(axis=-1, momentum=0.9997, scale=False)(x)
        x = Activation("relu")(x)
    return x


def stem(x_input):
    with K.name_scope('stem'):
        x = conv_block(x_input, 32, 3, 3, strides=(2, 2), padding='valid')
        x = conv_block(x, 32, 3, 3, padding='valid')
        x = conv_block(x, 64, 3, 3)

        x1 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid')(x)
        x2 = conv_block(x, 96, 3, 3, strides=(2, 2), padding='valid')

        x = concatenate([x1, x2], axis=-1)

        x1 = conv_block(x, 64, 1, 1)
        x1 = conv_block(x1, 96, 3, 3, padding='valid')

        x2 = conv_block(x, 64, 1, 1)
        x2 = conv_block(x2, 64, 7, 1)
        x2 = conv_block(x2, 64, 1, 7)
        x2 = conv_block(x2, 96, 3, 3, padding='valid')

        x = concatenate([x1, x2], axis=-1)

        x1 = conv_block(x, 192, 3, 3, strides=(2, 2), padding='valid')
        x2 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid')(x)

        merged_vector = concatenate([x1, x2], axis=-1)
    return merged_vector


def inception_A(x_input):
    """35*35 卷积块"""
    global INCEPTION_A_COUNT
    INCEPTION_A_COUNT += 1
    with K.name_scope('inception_A' + str(INCEPTION_A_COUNT)):
        averagepooling_conv1x1 = AveragePooling2D(pool_size=(3, 3), strides=(1, 1), padding='same')(
            x_input)  # 35 * 35 * 192
        averagepooling_conv1x1 = conv_block(averagepooling_conv1x1, 96, 1, 1)  # 35 * 35 * 96

        conv1x1 = conv_block(x_input, 96, 1, 1)  # 35 * 35 * 96

        conv1x1_3x3 = conv_block(x_input, 64, 1, 1)  # 35 * 35 * 64
        conv1x1_3x3 = conv_block(conv1x1_3x3, 96, 3, 3)  # 35 * 35 * 96

        conv3x3_3x3 = conv_block(x_input, 64, 1, 1)  # 35 * 35 * 64
        conv3x3_3x3 = conv_block(conv3x3_3x3, 96, 3, 3)  # 35 * 35 * 96
        conv3x3_3x3 = conv_block(conv3x3_3x3, 96, 3, 3)  # 35 * 35 * 96

        merged_vector = concatenate([averagepooling_conv1x1, conv1x1, conv1x1_3x3, conv3x3_3x3],
                                    axis=-1)  # 35 * 35 * 384
    return merged_vector


def inception_B(x_input):
    """17*17 卷积块"""
    global INCEPTION_B_COUNT
    INCEPTION_B_COUNT += 1
    with K.name_scope('inception_B' + str(INCEPTION_B_COUNT)):
        averagepooling_conv1x1 = AveragePooling2D(pool_size=(3, 3), strides=(1, 1), padding='same')(x_input)
        averagepooling_conv1x1 = conv_block(averagepooling_conv1x1, 128, 1, 1)

        conv1x1 = conv_block(x_input, 384, 1, 1)

        conv1x7_1x7 = conv_block(x_input, 192, 1, 1)
        conv1x7_1x7 = conv_block(conv1x7_1x7, 224, 1, 7)
        conv1x7_1x7 = conv_block(conv1x7_1x7, 256, 1, 7)

        conv2_1x7_7x1 = conv_block(x_input, 192, 1, 1)
        conv2_1x7_7x1 = conv_block(conv2_1x7_7x1, 192, 1, 7)
        conv2_1x7_7x1 = conv_block(conv2_1x7_7x1, 224, 7, 1)
        conv2_1x7_7x1 = conv_block(conv2_1x7_7x1, 224, 1, 7)
        conv2_1x7_7x1 = conv_block(conv2_1x7_7x1, 256, 7, 1)

        merged_vector = concatenate([averagepooling_conv1x1, conv1x1, conv1x7_1x7, conv2_1x7_7x1], axis=-1)
    return merged_vector


def inception_C(x_input):
    """8*8 卷积块"""
    global INCEPTION_C_COUNT
    INCEPTION_C_COUNT += 1
    with K.name_scope('Inception_C' + str(INCEPTION_C_COUNT)):
        averagepooling_conv1x1 = AveragePooling2D(pool_size=(3, 3), strides=(1, 1), padding='same')(x_input)
        averagepooling_conv1x1 = conv_block(averagepooling_conv1x1, 256, 1, 1)

        conv1x1 = conv_block(x_input, 256, 1, 1)

        # 用 1x3 和 3x1 替代 3x3
        conv3x3_1x1 = conv_block(x_input, 384, 1, 1)
        conv3x3_1 = conv_block(conv3x3_1x1, 256, 1, 3)
        conv3x3_2 = conv_block(conv3x3_1x1, 256, 3, 1)

        conv2_3x3_1x1 = conv_block(x_input, 384, 1, 1)
        conv2_3x3_1x1 = conv_block(conv2_3x3_1x1, 448, 1, 3)
        conv2_3x3_1x1 = conv_block(conv2_3x3_1x1, 512, 3, 1)
        conv2_3x3_1x1_1 = conv_block(conv2_3x3_1x1, 256, 3, 1)
        conv2_3x3_1x1_2 = conv_block(conv2_3x3_1x1, 256, 1, 3)

        merged_vector = concatenate(
            [averagepooling_conv1x1, conv1x1, conv3x3_1, conv3x3_2, conv2_3x3_1x1_1, conv2_3x3_1x1_2], axis=-1)
    return merged_vector


def reduction_A(x_input, k=192, l=224, m=256, n=384):
    with K.name_scope('Reduction_A'):
        """Architecture of a 35 * 35 to 17 * 17 Reduction_A block."""
        maxpool = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid')(x_input)

        conv3x3 = conv_block(x_input, n, 3, 3, strides=(2, 2), padding='valid')

        conv2_3x3 = conv_block(x_input, k, 1, 1)
        conv2_3x3 = conv_block(conv2_3x3, l, 3, 3)
        conv2_3x3 = conv_block(conv2_3x3, m, 3, 3, strides=(2, 2), padding='valid')

        merged_vector = concatenate([maxpool, conv3x3, conv2_3x3], axis=-1)
    return merged_vector


def reduction_B(x_input):
    """Architecture of a 17 * 17 to 8 * 8 Reduction_B block."""
    with K.name_scope('Reduction_B'):
        maxpool = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding='valid')(x_input)

        conv3x3 = conv_block(x_input, 192, 1, 1)
        conv3x3 = conv_block(conv3x3, 192, 3, 3, strides=(2, 2), padding='valid')

        conv1x7_7x1_3x3 = conv_block(x_input, 256, 1, 1)
        conv1x7_7x1_3x3 = conv_block(conv1x7_7x1_3x3, 256, 1, 7)
        conv1x7_7x1_3x3 = conv_block(conv1x7_7x1_3x3, 320, 7, 1)
        conv1x7_7x1_3x3 = conv_block(conv1x7_7x1_3x3, 320, 3, 3, strides=(2, 2), padding='valid')

        merged_vector = concatenate([maxpool, conv3x3, conv1x7_7x1_3x3], axis=-1)
    return merged_vector


def inception_v4_backbone(nb_classes=1000, load_weights=True):
    x_input = Input(shape=(299, 299, 3))
    # Stem
    x = stem(x_input)  # 35 x 35 x 384
    # 4 x Inception_A
    for i in range(2):
        x = inception_A(x)  # 35 x 35 x 384
    # Reduction_A
    x = reduction_A(x, k=192, l=224, m=256, n=384)  # 17 x 17 x 1024
    # 7 x Inception_B
    for i in range(3):
        x = inception_B(x)  # 17 x 17 x1024
    # Reduction_B
    x = reduction_B(x)  # 8 x 8 x 1536
    # Average Pooling
    x = AveragePooling2D(pool_size=(8, 8))(x)  # 1536
    # dropout
    x = Dropout(0.2)(x)
    x = Flatten()(x)  # 1536
    # 全连接层
    x = Dense(units=nb_classes, activation='softmax')(x)
    model = Model(inputs=x_input, outputs=x, name='Inception-V4')
    return model

这两种不同的模型构建方式,所用的预测函数是不一样的。

在第一种方式中,使用如下的预测方法:

    model.load_weights('c:/myvgg16.h5')
    classes = model.predict_classes(x_test)[0]
    classlist = model.predict_proba(x_test).tolist()  # 获取每个类的概率

predict_classes返回的是输入所属于的类别,predict_proba返回的是每个类别的概率,一般由于不能100%的预测分类,所以第二个函数用的比较多。

第二种方式的预测函数如下:

    classes = inception_v4_backbone.predict(x_test)[0]  

这个函数和predict_proba类似,返回每个类的概率。

第三种方式如下:

或者使用如这篇文章中所说的方式进行预测,即使用数据生成器进行预测:

https://blog.csdn.net/qq_27261889/article/details/85239164

但这样有个很大的问题,就是不能对具体的那个文件进行预测,而只能对文件夹进行预测,用起来不是很方便。

优点在于如果需要一次性分类很多图片,没有内存的限制。

------------------------------------------------分割线---------------------------------------------------------------

其中尤其要注意的一点是,在模型的训练过程中,为了提高模型的准确度,会把整形的图片数据变成浮点型。

对应上面的方式分为

    x_test.append(np.array(Image.open("c:/1.jpg").convert('RGB')))
    x_test = np.array(x_test)
    x_test = x_test.astype('float32')
    x_test /= 255


    train_datagen = ImageDataGenerator(
        rescale=1. / 255
    )

    val_datagen = ImageDataGenerator(
        rescale=1. / 255
    )


    inception_v4_model = inception_v4(nb_classes=534)

    train_generator = train_datagen.flow_from_directory(directory='C:/train',
                                                        target_size=(299, 299), 
                                                        batch_size=32,
                                                        shuffle=True
                                                        )

    val_generator = val_datagen.flow_from_directory(directory='C:/test',
                                                    target_size=(299, 299),
                                                    batch_size=32,
                                                    shuffle=True
                                                    )

所以在预测的时候,同样需要把输入的图片进行浮点化的处理,否则可能出现,不论输入什么图片,都输出同一个类别的错误。