Downloaded keras_model.h5 is not working - ValueError: Unknown layer: Functional

[hs1003]

I downloaded keras weight file and call "model = tensorflow.keras.models.load_model('converted_keras/keras_model.h5')".
But it is not working with some error log.
I have a weight file when I downloaded in October, this model file is perfectly working.
But now, it is not working with this error.
Please help me!
=====================[ Error Log ] ==================
c:\users\pc\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\utils\generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
178 config = identifier
179 (cls, cls_config) = class_and_config_for_serialized_keras_object(
--> 180 config, module_objects, custom_objects, printable_module_name)
181
182 if hasattr(cls, 'from_config'):

c:\users\pc\appdata\local\programs\python\python37\lib\site-packages\tensorflow_core\python\keras\utils\generic_utils.py in class_and_config_for_serialized_keras_object(config, module_objects, custom_objects, printable_module_name)
163 cls = module_objects.get(class_name)
164 if cls is None:
--> 165 raise ValueError('Unknown ' + printable_module_name + ': ' + class_name)
166 return (cls, config['config'])
167

ValueError: Unknown layer: Functional

[cenzwong]

Upgrade the tensorflow to version 2.3.x, this might solve your problem.

When updating tensorflow, you might encounter this error:

After October 2020 you may experience errors when installing or updating package
s. This is because pip will change the way that it resolves dependency conflicts. 

We recommend you use --use-feature=2020-resolver to test your packages with the new res
olver before it becomes the default.

just run this to upgrade your tensorflow

!pip install --upgrade tensorflow --use-feature=2020-resolver