Custom loss function including output of layer - python-3.x

Question

I have a dataset that contains 1 value of y_true per case. I want to build a DNN that outputs 3 coefficients that will later be used as follows to create y_pred
y_pred = 4*coeff_1 + 5*coeff_2 + 6 *coeff_3
I am using keras and when i tried to define a custom function like this
from keras.callbacks import ModelCheckpoint
from keras.layers import advanced_activations
from keras.models import Sequential
from keras.layers import Dense, Activation, Flatten
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
import keras.backend as K
def custom_objective(layer):
return K.sum(layer.output)
NN_model = Sequential()
# The Input Layer :
NN_model.add(Dense(X_train.shape[1], kernel_initializer='normal',input_dim = X_train.shape[1], activation='relu'))
# The Hidden Layers :
NN_model.add(Dense(20, kernel_initializer='normal',activation='elu'))
NN_model.add(Dense(20, kernel_initializer='normal',activation='elu'))
output_layer = Dense(1, kernel_initializer='normal',activation='linear')
# The Output Layer :
NN_model.add(output_layer)
# Compile the network :
NN_model.compile(loss=custom_objective(output_layer), optimizer='Adamax', metrics=['mean_absolute_error'])
NN_model.summary()
NN_model.fit(X_train, y_train, epochs=10,verbose = 1)
print('NN train = ', mean_absolute_error(y_train , NN_model.predict(X_train)))
predictions = NN_model.predict(X_test)
MAE = mean_absolute_error(y_test , predictions)
print('NN MAE = ', MAE)
I get all
TypeError: Using a tf.Tensor as a Python bool is not allowed. Use
if t is not None: instead of if t: to test if a tensor is defined,
and use TensorFlow ops such as tf.cond to execute subgraphs
conditioned on the value of a tensor.
So my question is
How can I define a DNN that will take 1 y_true per data, output 3 values which it will combine linearly to assemble a y_pred which will be used to get the loss function and train the network
Thank you for your time

Answer 1

How about something along these lines?
from keras.models import Model
from keras.layers import Dense, Input, Add, Lambda
def model(inp_size):
inp = Input(shape=(inp_size, 1))
x1 = Dense(20, activation='elu')(inp)
x1 = Dense(20, activation='elu')(x1)
x1 = Dense(1, activation = 'linear')(x1)
x2 = Dense(20, activation='elu')(inp)
x2 = Dense(20, activation='elu')(x2)
x2 = Dense(1, activation = 'linear')(x2)
x3 = Dense(20, activation='elu')(inp)
x3 = Dense(20, activation='elu')(x3)
x3 = Dense(1, activation = 'linear')(x3)
x1 = Lambda(lambda x: x * 4.0)(x1)
x2 = Lambda(lambda x: x * 5.0)(x2)
x3 = Lambda(lambda x: x * 6.0)(x3)
out = Add()([x1, x2, x3])
return Model(inputs = inp, outputs = out)