tensorflow - 'Model' object has no attribute 'load_model' keras -

i'm trying load model saved with: model.save('mymodel.h5')

the model defined this:

self.model = vggface(input_tensor=input_tensor, include_top=true)  layer in self.model.layers:     layer.trainable = false  self.model.get_layer('fc7').trainable = true last_layer = self.model.get_layer('fc7').output out = batchnormalization()(last_layer) out = dense(self.n_outputs, activation='softmax', name='fc8')(out) self.model = model(input=self.model.input, output=out) 

when try load mymodel.h5 model.load_model('mymodel.h5') throws me following error:

attributeerror: 'model' object has no attribute 'load_model' 

i supose it's because i'm not working sequential models.

how can load model then? since model.save('mymodel.h5') seems work.

thanks!!!!

load_model() isn't attribute of model obejct indeed. load_model() function imported keras.models takes file name , returns model obejct.

you should use :

from keras.models import load_model  model = load_model(path_to_model) 

you can use keras.models.load_model(filepath) reinstantiate model. load_model take care of compiling model using saved training configuration (unless model never compiled in first place). from source