Unknown layer: KerasLayer when i try to load_model
Question:
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
Answers:
I just found a solution that worked for me
my_reloaded_model = tf.keras.models.load_model(
(path),
custom_objects={'KerasLayer':hub.KerasLayer}
)
ı had this problem
ValueError: Unknown layer: patch_extract. 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.
and ı was trying your solution:
model = load_model(‘version.h5’, custom_objects={‘patch_extract’: hub.patch_extract})
afther this, ı had this error: AttributeError: module ‘tensorflow_hub’ has no attribute ‘patch_extract’
how can ı solution this error?
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
I just found a solution that worked for me
my_reloaded_model = tf.keras.models.load_model(
(path),
custom_objects={'KerasLayer':hub.KerasLayer}
)
ı had this problem
ValueError: Unknown layer: patch_extract. 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.
and ı was trying your solution:
model = load_model(‘version.h5’, custom_objects={‘patch_extract’: hub.patch_extract})
afther this, ı had this error: AttributeError: module ‘tensorflow_hub’ has no attribute ‘patch_extract’
how can ı solution this error?