在Keras中,输入x*a
是否可能size(None, None, 3)
?例如,输入x
和constant a: x(batch,None,None,1024)*a(batch,1)
。
我在训练中使用输入size (64, 64, 3)
,但测试数据应使用可变的输入大小。无法调整测试尺寸以进行公平的图像处理。
我尝试使用Lambda function(lambda x : x * a)(seq)
。然后,我在代码中没有问题。然后,启动model.fit函数,出现错误:
------------->>tensorflow.python.framework.errors_impl.InvalidArgumentError: Incompatible shapes: [7,4,4,1024] vs. [7,1].
。
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)
conv_c = Conv2D(num_classes, 1, activation='softmax')(conv5)
conv_c1 = GlobalAveragePooling2D(name="class_output")(conv_c)
conv_c1_1 = conv_c1[:, 0:1]
conv_c1_2 = conv_c1[:, 1:2]
conv_c1_3 = conv_c1[:, 2:3]
conv5_b = Lambda(lambda x: x * conv_c1_1)(conv5) #conv5:Tensor(shape=(?, 4, 4, 1024))
conv5_h = Lambda(lambda x: x * conv_c1_2)(conv5) #conv_c1_1: Tensor(shape=(?, 1))
conv5_r = Lambda(lambda x: x * conv_c1_3)(conv5)