Train only age about age-gender-estimation

[Zumbalamambo]

@yu4u since I want only the age, I tried getting the the as follows,

 predictions_a = Dense(units=101, kernel_initializer=self._weight_init, use_bias=self._use_bias,
                              kernel_regularizer=l2(self._weight_decay), activation="softmax")(flatten)

        model = Model(inputs=inputs, outputs=[ predictions_a])

        return model

however,it throws the following error,

Traceback (most recent call last):
File "wideres_conv.py", line 17, in
model.load_weights("input/weights.18-4.06.hdf5")
File "C:\Program Files\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2572, in load_weights
load_weights_from_hdf5_group(f, self.layers)
File "C:\Program Files\Anaconda3\lib\site-packages\keras\engine\topology.py", line 3021, in load_weights_from_hdf5_group
str(len(filtered_layers)) + ' layers.')
ValueError: You are trying to load a weight file containing 31 layers into a model with 30 layers.