我想使用 DSSIM 損失函數(shù)，我把這個(gè)損失函數(shù)的代碼放在我的代碼中，但它產(chǎn)生了這個(gè)錯(cuò)誤回溯（最近一次調(diào)用最后一次）：文件“”，第 218 行，在 w_extraction.compile(optimizer=opt, loss={'decoder_output':'DSSIMObjective','wprim':'binary_crossentropy'}, loss_weights={'decoder_output': 1.0, 'wprim': 1.0 },metrics=['mae'])文件“D:\software\Anaconda3\envs\py36\lib\site-packages\keras\engine\training.py”，第 129 行，編譯 loss_functions.append(losses.get(loss.get(name)))文件“D:\software\Anaconda3\envs\py36\lib\site-packages\keras\losses.py”，第 133 行，在 get 中返回反序列化（標(biāo)識(shí)符）文件“D:\software\Anaconda3\envs\py36\lib\site-packages\keras\losses.py”，第114行，反序列化printable_module_name='loss function'）文件 "D:\software\Anaconda3\envs\py36\lib\site-packages\keras\utils\generic_utils.py"，第 165 行，在 deserialize_keras_object ':' + function_name)ValueError：未知損失函數(shù)：DSSIMObjective我不知道我應(yīng)該把這個(gè)損失函數(shù)的定義放在哪里？我把這段代碼放在我的網(wǎng)絡(luò)結(jié)構(gòu)之上。import keras_contrib.backend as KCclass DSSIMObjective:    """Difference of Structural Similarity (DSSIM loss function).    Clipped between 0 and 0.5    Note : You should add a regularization term like a l2 loss in addition to this one.    Note : In theano, the `kernel_size` must be a factor of the output size. So 3 could           not be the `kernel_size` for an output of 32.    # Arguments        k1: Parameter of the SSIM (default 0.01)        k2: Parameter of the SSIM (default 0.03)        kernel_size: Size of the sliding window (default 3)        max_value: Max value of the output (default 1.0)    """    def __init__(self, k1=0.01, k2=0.03, kernel_size=3, max_value=1.0):        self.__name__ = 'DSSIMObjective'        self.kernel_size = kernel_size        self.k1 = k1        self.k2 = k2        self.max_value = max_value        self.c1 = (self.k1 * self.max_value) ** 2        self.c2 = (self.k2 * self.max_value) ** 2        self.dim_ordering = K.image_data_format()        self.backend = K.backend()    def __int_shape(self, x):        return K.int_shape(x) if self.backend == 'tensorflow' else K.shape(x)