TimeDistributed with Dense does not mask bias

TimeDistributedDenseWithMask.py

import numpy as np
from keras.models import Model
from keras.layers import Masking, Input, TimeDistributed, Dense

# Construct time series data set
pad_value = 0.1

t1 = [3, 1, 2, 0.1]
t2 = [1, 1, 1, 0.1]
t_pad = [pad_value, pad_value, pad_value, pad_value]
time_series = np.asarray([[t1, t2, t_pad]])

###############################################################################################

def build_model(use_masking, add_constant, mask_value=pad_value):
    """Build a network that sums the values at each time step in a time series.
     
    Arguments:
        - use_masking: Boolean to activate a masking layer to mask mask_value 
        - add_constant: Constant to add to the sum. This will be the bias value in the network. 
        
    Returns:
        - Keras model
        
    We will construct a neural network with a linear activation function, 
    and we will manually set the weights to 1 and the bias to add_constant.
    """
    my_input = Input(shape=(None, 4))
    
    if use_masking:
        mask = Masking(mask_value=mask_value)(my_input)
        out = TimeDistributed(Dense(1, activation='linear'))(mask)
    else:
        out = TimeDistributed(Dense(1, activation='linear'))(my_input)
        
    model = Model(inputs=my_input, outputs=out)
    
    # Set all weights multiplying the input to 1, and set the bias to add_constant
    model.set_weights([np.ones_like(model.get_weights()[0]),
                       add_constant*np.ones_like(model.get_weights()[1])])
    return model

def print_helper(time_series_sum):
    s1, s2, s3 = time_series_sum
    print("Sum t1 \t  = ", s1[0])
    print("Sum t2 \t  = ", s2[0])
    print("Sum t_pad = ", s3[0])
    
###############################################################################################
# Test model
###############################################################################################

print("Manuel sum of time series steps (without any masking)")
print_helper([[np.sum(t1)], [np.sum(t2)], [np.sum(t_pad)]])
print()

### Test 1
print("Test 1: ")
print("use_masking = False")
print("add_constant = 0")
time_series_sum_test_1 = build_model(use_masking=False, add_constant = 0).predict(time_series)[0]
print_helper(time_series_sum_test_1)
print("This works as expected \n")

### Test 2
print("Test 2: ")
print("use_masking = False")
print("add_constant = 10")
time_series_sum_test_1 = build_model(use_masking=False, add_constant = 10).predict(time_series)[0]
print_helper(time_series_sum_test_1)
print("This works as expected \n")

### Test 3
print("Test 3: ")
print("use_masking = True")
print("add_constant = 0")
time_series_sum_test_1 = build_model(use_masking=True, add_constant = 0).predict(time_series)[0]
print_helper(time_series_sum_test_1)
print("This is a check that masking works as expected on the weights multiplying the inputs. \n(Note: The bias is now set to zero) \n")

### Test 4
print("Test 4: ")
print("use_masking = True")
print("add_constant = 10")
time_series_sum_test_1 = build_model(use_masking=True, add_constant = 10).predict(time_series)[0]
print_helper(time_series_sum_test_1)
print("This fails! sum of t_pad is equal to the bias in the network \nThe masking layer is not masking the bias!")