时间戳

首页 > 解决方案 > TypeError: 不支持的操作数类型 /: 'float' 和 'Dimension'，请使用 // 代替

python - TypeError: 不支持的操作数类型 /: 'float' 和 'Dimension'，请使用 // 代替

问题描述

当我尝试从 UNet 模型内部调用 RA_unit_v4_1 方法时，出现以下错误。我使用 x.shape[y].value 方法转换了所有维度值，但它没有帮助。x 和 conv_n 的形状都是一样的。如何解决此问题或导致此问题发生的原因？

错误

TypeError: unsupported operand type(s) for /: 'float' and 'Dimension', please use // instead

RA_unit_v4_1

def RA_unit_v4_1(x, h, w, n):
    x_1_n = MaxPooling2D(pool_size=(int(h/n), 2), strides=(int(h/n),2), padding='same', data_format='channels_last')(x)
    x_t_n = K.zeros([1, h, w, 0], K.floatx())

    for k in range(n):
        x_t_1_n =K.slice(x_1_n, [0,k,0,0], [1,1,int(w/2),x.shape[3].value])
        x_t_2_n = K.resize_images(x_t_1_n, int(h//x_t_1_n.shape[1].value), int(w//x_t_1_n.shape[2].value), data_format='channels_last',interpolation='nearest')
        x_t_3_n = K.abs(x - x_t_2_n)
        x_t_n = concatenate([x_t_n, x_t_3_n], axis=3)

    x_out_n = concatenate([x, x_t_n], axis=3)
    conv_n = Conv2D(x.shape[3], 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(x_out_n)

    return conv_n

网络模型

def unet(pretrained_weights = None,input_size = None):
    inputs = Input(batch_shape=input_size)

    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(inputs)
    conv1 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv1)

    pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

    RA_1 = RA_unit_v4_1(x=pool1,h=pool1.shape[1].value, w=pool1.shape[2].value,n=16)

    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(RA_1)
    conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv2)
    pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)



    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool2)
    conv3 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv3)
    pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)



    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool3)
    conv4 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv4)
    drop4 = Dropout(0.5)(conv4)
    pool4 = MaxPooling2D(pool_size=(2, 2))(drop4)



    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(pool4)
    conv5 = Conv2D(1024, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv5)
    drop5 = Dropout(0.5)(conv5)

    up6 = Conv2D(512, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(drop5))
    merge6 = concatenate([drop4,up6], axis = 3)



    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge6)
    conv6 = Conv2D(512, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv6)

    up7 = Conv2D(256, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv6))
    merge7 = concatenate([conv3,up7], axis = 3)



    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge7)
    conv7 = Conv2D(256, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv7)

    up8 = Conv2D(128, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv7))
    merge8 = concatenate([conv2,up8], axis = 3)



    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge8)
    conv8 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv8)

    up9 = Conv2D(64, 2, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(UpSampling2D(size = (2,2))(conv8))
    merge9 = concatenate([conv1,up9], axis = 3)



    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(merge9)
    conv9 = Conv2D(64, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)
    conv9 = Conv2D(2, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(conv9)

    conv10 = Conv2D(3, 1, activation = 'sigmoid')(conv9)

    model = Model(input = inputs, output = conv10)

    model.compile(optimizer = Adam(lr = 1e-4), loss = 'binary_crossentropy', metrics = ['accuracy']) # original 1e-4 | 2e-4 = 0.00020

    model.summary()

    if(pretrained_weights):
        model.load_weights(pretrained_weights)

    return model

标签： pythonpython-3.xtensorflowkeras

解决方案

我解决了。它在方法 RA_unit_v4_1 的最后一行之前；

conv_n = Conv2D(x.shape[3], 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(x_out_n)

经过

conv_n = Conv2D(x.shape[3].value, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(x_out_n)

即 x.shape[3] 应该替换为 x.shape[3].value。

解决后出现以下错误。'AttributeError: 'NoneType' 对象没有属性 '_inbound_nodes'' 。要解决此问题，应使用 lambda 函数。它如下：

pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)

RA_1 = Lambda(lambda y: RA_unit_v4_1(x=y, h=y.shape[1].value, w=y.shape[2].value, n=16) )
RA_1_n = RA_1(pool1)

conv2 = Conv2D(128, 3, activation = 'relu', padding = 'same', kernel_initializer = 'he_normal')(RA_1_n)

推荐阅读