对一系列图像使用 categorical_crossentropy

如何解决对一系列图像使用 categorical_crossentropy

我有一个模型，它接受一系列图像作为输入 (None,n_step,128,128)（而不是单个图像），其中 n_step 是固定数字 10。我使用 categorical_crossentropy 对四类问题进行分类。但是我有一个错误，如下所示

ValueError: A target array with shape (1342,10,4) was passed for an output of shape (None,1,4) while using as loss `categorical_crossentropy`. This loss expects targets to have the same shape as the output.

我从错误中了解到，它一次只需要一个图像。有什么方法可以将这种损失用于一系列图像吗？

模型的输出也将是一组10标签

编辑：

n_steps = 10
feature_count = 4
def create_model():

    trajectory_input = Input(shape=(n_steps,feature_count),name='trajectory_input')
    image_input  = Input(shape=(128,n_steps),name='image_input')

    x_aware = (Conv2D(32,kernel_size=(3,3),activation='relu'))(image_input)
    x_aware = (Batchnormalization())(x_aware)
    x_aware = (MaxPooling2D(pool_size=(2,2)))(x_aware)
    x_aware = (Dropout(0.25))(x_aware)

    x_aware = (Conv2D(64,activation='relu'))(x_aware)
    x_aware = (Batchnormalization())(x_aware)
    x_aware = (MaxPooling2D(pool_size=(2,2)))(x_aware)
    x_aware = (Dropout(0.25))(x_aware)

    x_aware = (Dense(64,activation='relu',kernel_regularizer=regularizers.l2(0.001)))(x_aware)
    x_aware = (Batchnormalization())(x_aware)
    x_aware = (Dropout(0.25))(x_aware)
    x_aware = Reshape((1,12544))(x_aware)

    x = (Dense(32,kernel_regularizer=regularizers.l2(0.001)))(trajectory_input)
    x = Reshape((1,32*n_steps))(x)

    x = concatenate([x,x_aware])
    x = (Dense(64,kernel_regularizer=regularizers.l2(0.001)))(x)
    x = (Dense(32,kernel_regularizer=regularizers.l2(0.001)))(x)

    x_reg = (Dense(8,kernel_regularizer=regularizers.l2(0.001)))(x)
    x_class = (Dense(8,kernel_regularizer=regularizers.l2(0.001)))(x)

    x_reg = Reshape((2,4))(x_reg)

    output_regression = (Dense(2,name='main_output'))(x_reg)
    output_class = (Dense(4,name='classification_output',activation='softmax'))(x_class)

    adam = Adam(lr=learning_rate)
    model = Model(inputs=[trajectory_input,image_input],outputs=[output_regression,output_class])
    model.compile(optimizer=adam,loss={'main_output': 'mse','classification_output': 'categorical_crossentropy'},metrics={'main_output': [euc_dist_1,euc_dist_2],'classification_output': 'accuracy'})
    model.summary()
    return model

输入是回归任务的图像及其相关信息，输出是标签和下一个可预测值。

解决方法

问题在于给分类任务的 Dense 和 Reshape 层的输入。由于输入在 (10,128,128) 中，因此单位数应为 10*num_class。所以改变这个

x_reg = (Dense(8,activation='relu',kernel_regularizer=regularizers.l2(0.001)))(x)
x_class = (Dense(8,kernel_regularizer=regularizers.l2(0.001)))(x)

x_reg = Reshape((2,4))(x_reg)

output_regression = (Dense(2,name='main_output'))(x_reg)
output_class = (Dense(4,name='classification_output',activation='softmax'))(x_class)

这样就解决了问题

x_reg = (Dense(8,kernel_regularizer=regularizers.l2(0.001)))(x)
x_class = (Dense(40,4))(x_reg)
x_class = Reshape((10,4))(x_class)

output_regression = (Dense(2,activation='softmax'))(x_class)