Unable to Load Saved Model

[rohanneps]

I trained the model on a custom dataset using a custom generator as opposed to loading in-memory and have saved the Keras sequential model using the ModelCheckpoint callback.

However, on loading model as model = load_model('..'), I get the following error:

Traceback (most recent call last):
File "predict.py", line 25, in
model = load_model(os.path.join('models','binary_custom.hdf5'))
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/saving.py", line 419, in load_model
model = _deserialize_model(f, custom_objects, compile)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/saving.py", line 225, in _deserialize_model
model = model_from_config(model_config, custom_objects=custom_objects)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/saving.py", line 458, in model_from_config
return deserialize(config, custom_objects=custom_objects)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/layers/init.py", line 55, in deserialize
printable_module_name='layer')
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 145, in deserialize_keras_object
list(custom_objects.items())))
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/network.py", line 1022, in from_config
process_layer(layer_data)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/network.py", line 1008, in process_layer
custom_objects=custom_objects)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/layers/init.py", line 55, in deserialize
printable_module_name='layer')
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 145, in deserialize_keras_object
list(custom_objects.items())))
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/sequential.py", line 300, in from_config
custom_objects=custom_objects)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/layers/init.py", line 55, in deserialize
printable_module_name='layer')
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 147, in deserialize_keras_object
return cls.from_config(config['config'])
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/engine/base_layer.py", line 1109, in from_config
return cls(**config)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/layers/convolutional.py", line 490, in init
**kwargs)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/layers/convolutional.py", line 117, in init
self.kernel_initializer = initializers.get(kernel_initializer)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/initializers.py", line 511, in get
return deserialize(config)
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/initializers.py", line 503, in deserialize
printable_module_name='initializer')
File "/home/ubuntu/image_matching/env/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 138, in deserialize_keras_object
': ' + class_name)
ValueError: Unknown initializer: initialize_weights

My python version is 3.6.7 with Keras==2.2.4 and tensorflow==1.13.1.

Any suggestions would be higly appreciated.

[rohanneps]

SOLVED!

For anyone facing the same issue, please note that we would need to pass the custom weight and bias initializer functions as custom objects through a callable(class) as shown below
...
from keras.utils.generic_utils import get_custom_objects
def initialize_weights(shape, name=None):
# same function as in training script
return np.random.normal(loc = 0.0, scale = 1e-2, size = shape)

class CustomWeightInitializer:
def call(self, shape):
return initialize_weights(shape)

get_custom_objects().update({'initialize_weights': CustomWeightInitializer,'initialize_bias': CustomBiasInitializer})

model = load_model('...')