keras.backend is not defined for variational autoencoder model - keras

Question

I created a Variational Autoencoder model. To do the sampling, I created the following method:
from keras import backend as k
def sampling(args):
z_mean , z_log_var=args
batch=k.shape(z_mean)[0]
dim=k.int_shape(z_mean)[1]
epsilon=k.random_normal(shape=(batch,dim))
return z_mean + k.exp(0.5 * z_log_var) * epsilon
this is the model architecture:
def create_variationalModel(original_dim):
input_shape=(original_dim,)
intermidiate_dim=58
batch_size=10
latent_dim=3
epochs=100
inputs=Input(shape=input_shape,name="encoder_input")
x= Dense(units=original_dim,activation="tanh")(inputs)
x= Dense(units=int(original_dim/2),activation="tanh")(x)
x1= Dense(units=int(original_dim/4),activation="tanh")(x)
x2= Dense(units=int(original_dim/8),activation="tanh")(x1)
x3= Dense(units=10,activation="tanh")(x2)
z_mean=Dense(latent_dim,name="z_mean")(x3)
z_log_var=Dense(latent_dim,name="z_log_var")(x3)
z=Lambda(sampling,output_shape=(latent_dim,),name="z")([z_mean,z_log_var])
encoder=Model(inputs,[z_mean,z_log_var,z],name="encoder")
encoder.summary()
latent_inputs=Input(shape=(latent_dim,),name="z_sampling")
x= Dense(units=10,activation="tanh")(latent_inputs)
x1=Dense(units=int(original_dim/8),activation="tanh")(x)
x2=Dense(units=int(original_dim/4),activation="tanh")(x1)
x3=Dense(units=int(original_dim/2),activation="tanh")(x2)
x3=Dense(units=original_dim,activation="tanh")(x3)
outputs=Dense(units=original_dim,activation="sigmoid")(x3)
decoder=Model(latent_inputs,outputs,name="decoder")
decoder.summary()
outputs=decoder(encoder(inputs)[2])
vae = Model(inputs,outputs,name="vae_mlp")
reconstruction_loss=mse(inputs,outputs)
reconstruction_loss*=original_dim
kl_loss = 1 + z_log_var -k.square(z_mean) - k.exp(z_log_var)
kl_loss=k.sum(kl_loss,axis=-1)
kl_loss*=-0.5
vae_loss=k.mean(reconstruction_loss+kl_loss)
vae.add_loss(vae_loss)
plot_model(vae,to_file='vae.png',show_shapes=True)
vae.compile(optimizer=RMSprop(),loss="mean_squared_error",metrics=["mae"])
return vae
the after training the model and test it, I decide to save it like this:
vae.save("./models/vae.h5")
but when I tried to load the model like this:
model = load_model("./models/vae.h5")
I have this issue:
--------------------------------------------------------------------------- NameError Traceback (most recent call
last) in
1 #load model
----> 2 model = load_model("./models/vae.h5")
3 # summarize model.
4 model.summary()
5 with open("./models/LabelEncoders_dic.pickle","rb") as f:
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in load_wrapper(*args, **kwargs)
490 os.remove(tmp_filepath)
491 return res
--> 492 return load_function(*args, **kwargs)
493
494 return load_wrapper
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in load_model(filepath, custom_objects, compile)
582 if H5Dict.is_supported_type(filepath):
583 with H5Dict(filepath, mode='r') as h5dict:
--> 584 model = _deserialize_model(h5dict, custom_objects, compile)
585 elif hasattr(filepath, 'write') and callable(filepath.write):
586 def load_function(h5file):
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in _deserialize_model(h5dict, custom_objects, compile)
272 raise ValueError('No model found in config.')
273 model_config = json.loads(model_config.decode('utf-8'))
--> 274 model = model_from_config(model_config, custom_objects=custom_objects)
275 model_weights_group = h5dict['model_weights']
276
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/saving.py
in model_from_config(config, custom_objects)
625 'Sequential.from_config(config)?')
626 from ..layers import deserialize
--> 627 return deserialize(config, custom_objects=custom_objects)
628
629
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/init.py
in deserialize(config, custom_objects)
163 globs['Model'] = models.Model
164 globs['Sequential'] = models.Sequential
--> 165 return deserialize_keras_object(config,
166 module_objects=globs,
167 custom_objects=custom_objects,
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/utils/generic_utils.py
in deserialize_keras_object(identifier, module_objects,
custom_objects, printable_module_name)
142 custom_objects = custom_objects or {}
143 if has_arg(cls.from_config, 'custom_objects'):
--> 144 return cls.from_config(
145 config['config'],
146 custom_objects=dict(list(_GLOBAL_CUSTOM_OBJECTS.items()) +
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in from_config(cls, config, custom_objects) 1054 # First,
we create all layers and enqueue nodes to be processed 1055
for layer_data in config['layers']:
-> 1056 process_layer(layer_data) 1057 1058 # Then we process nodes in order of layer depth.
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in process_layer(layer_data) 1039 from ..layers import
deserialize as deserialize_layer 1040
-> 1041 layer = deserialize_layer(layer_data, 1042 custom_objects=custom_objects) 1043
created_layers[layer_name] = layer
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/init.py
in deserialize(config, custom_objects)
163 globs['Model'] = models.Model
164 globs['Sequential'] = models.Sequential
--> 165 return deserialize_keras_object(config,
166 module_objects=globs,
167 custom_objects=custom_objects,
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/utils/generic_utils.py
in deserialize_keras_object(identifier, module_objects,
custom_objects, printable_module_name)
142 custom_objects = custom_objects or {}
143 if has_arg(cls.from_config, 'custom_objects'):
--> 144 return cls.from_config(
145 config['config'],
146 custom_objects=dict(list(_GLOBAL_CUSTOM_OBJECTS.items()) +
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in from_config(cls, config, custom_objects) 1073
node_data = node_data_list[node_index] 1074
try:
-> 1075 process_node(layer, node_data) 1076 1077 # If the node does not have all
inbound layers
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/network.py
in process_node(layer, node_data) 1023 # and building
the layer if needed. 1024 if input_tensors:
-> 1025 layer(unpack_singleton(input_tensors), **kwargs) 1026 1027 def process_layer(layer_data):
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/backend/tensorflow_backend.py
in symbolic_fn_wrapper(*args, **kwargs)
73 if _SYMBOLIC_SCOPE.value:
74 with get_graph().as_default():
---> 75 return func(*args, **kwargs)
76 else:
77 return func(*args, **kwargs)
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/engine/base_layer.py
in call(self, inputs, **kwargs)
487 # Actually call the layer,
488 # collecting output(s), mask(s), and shape(s).
--> 489 output = self.call(inputs, **kwargs)
490 output_mask = self.compute_mask(inputs, previous_mask)
491
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/core.py
in call(self, inputs, mask)
714 else:
715 self._input_dtypes = K.dtype(inputs)
--> 716 return self.function(inputs, **arguments)
717
718 def compute_mask(self, inputs, mask=None):
~/anaconda3/envs/myenv/lib/python3.8/site-packages/keras/layers/core.py
in sampling(args)
NameError: name 'k' is not defined
K comes from from keras import backend as k. even y adding this importation, I have the same error. Can anyone know how to fix this ?