CODEWITHSUNDEEP
pythonkerastensorflow2.0
Assem Khaled
Assem Khaled

Reputation: 601

Unknown layer: KerasLayer when i try to load_model

When i try to save my model as hdf5

path = 'path.h5'
model.save(path)

then load the model again

my_reloaded_model = tf.keras.models.load_model(path)

I get the following error

ValueError: Unknown layer: KerasLayer

Any help ? I'm using

tensorflow version:  2.2.0  
keras version:  2.3.0-tf

Upvotes: 18

Views: 13892

Answers (2)

qmzp
qmzp

Reputation: 109

You may also face this problem if you have made a custom model and not included get_config method in the custom layers and models.

class CustomLayer(keras.layers.Layer):
    def __init__(self, sublayer, **kwargs):
        super().__init__(**kwargs)
        self.sublayer = layer

    def call(self, x):
        return self.sublayer(x)

    def get_config(self):
        base_config = super().get_config()
        config = {
            "sublayer": keras.saving.serialize_keras_object(self.sublayer),
        }
        return {**base_config, **config}

    @classmethod
    def from_config(cls, config):
        sublayer_config = config.pop("sublayer")
        sublayer = keras.saving.deserialize_keras_object(sublayer_config)
        return cls(sublayer, **config)

Check for more

Upvotes: 0

Assem Khaled
Assem Khaled

Reputation: 601

I just found a solution that worked for me

my_reloaded_model = tf.keras.models.load_model(
       (path),
       custom_objects={'KerasLayer':hub.KerasLayer}
)

Upvotes: 42

Related Questions