如何将张量张量转换为KERAS张量或调整KERAS特征图

Question

如何在 keras中调整特征映射或将 tensorflow tensor转换为 keras tensor？

我想调整keras层的大小，然后使用K.resize_images，但我失败了。

    block1_btchnorm2 = BatchNormalization(name ='b1_bn2')(block1_conv2)
    block1_conv3 = Conv2D(128, (3,3), activation='elu',name='b1_c3')(block1_btchnorm2)
    block1_btchnorm3 = BatchNormalization(name ='b1_bn3')(block1_conv3)
    block1_maxpooling =  MaxPooling2D(pool_size=(2,2),name ='b1_mp')(block1_btchnorm3)
    block1_out = K.resize_images(block1_maxpooling, height_factor =64/124 , width_factor = 64/124, data_format='channels_last')

attributeError：'tensor'对象没有属性'_keras_history'

Answer 1

您必须使用lambda层将任何后端功能应用于keras张量：

block1_out = Lambda(lambda x: K.resize_images(x, height_factor =64/124 , width_factor = 64/124, data_format='channels_last'))(block1_maxpooling)