Loading saved model fails

I've trained a model and saved it in .h5 format. when I try loading it I received this error

ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_588/661726548.py in module
      9 # returns a compiled model
     10 # identical to the previous one
--- 11 reconstructed_model = keras.models.load_model(./custom_model.h5)

~\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py in error_handler(*args, **kwargs)
     65     except Exception as e:  # pylint: disable=broad-except
     66       filtered_tb = _process_traceback_frames(e.__traceback__)
--- 67       raise e.with_traceback(filtered_tb) from None
     68     finally:
     69       del filtered_tb

~\Anaconda3\lib\site-packages\keras\utils\generic_utils.py in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
    560   cls = get_registered_object(class_name, custom_objects, module_objects)
    561   if cls is None:
-- 562     raise ValueError(
    563         f'Unknown {printable_module_name}: {class_name}. Please ensure this '
    564         'object is passed to the `custom_objects` argument. See '

ValueError: Unknown loss function: custom_loss_. Please ensure this object is passed to the `custom_objects` argument. See https://www.tensorflow.org/guide/keras/save_and_serialize#registering_the_custom_object for details.

saving line of code is customModel.mod_save(./custom_model.h5) loading line of code is reconstructed_model = keras.models.load_model(custom_model.h5) I've tried loading with absolute and relative paths and even without .h5

I think the problem is building a class for the model and custom loss function outside the class and i can't use .add_loss function and this happens for metrics too

here is a part of my class implemetation

class custom_Model():
    def __init__(self, inputs):
        self.inputs = inputs 
     def __call__(self):         
        self.build_model()

     def build_model(self):
        ......
        ......
        self.model = Model(inputs =  inputs, outputs = x7, name=req_cust_model)
     def save_model(self,filepath,overwrite=True,
                   include_optimizer=True,save_format=None,
                   signatures=None,options=None,save_traces=True):
        return tf.keras.models.save_model(self.model,filepath,overwrite=overwrite,
                                        include_optimizer=include_optimizer,
                                        save_format=save_format,
                                        signatures=signatures,options=options,
                                        save_traces=save_traces) 
   

custom loss function

class custom_loss(Loss):
    def __init__(self,alpha=0.25,beta=0.75):
        super().__init__()
        self.alpha=alpha
        self.beta=beta
    
    def call(self,y, y_pred):
        l1=tf.keras.losses.MeanSquaredError()        
        l2=tf.keras.losses.MeanSquaredLogarithmicError()        
        return self.alpha * l1 + self.beta * l2 

any idea how i can link a custom loss to a custom model implemented as shown above