Custom layer at top of Tensorflow model

Question

I want to add a Custom Layer to a Tensorflow Model which transforms every row of a the input set to the model in a set pattern.

For example, below is the custom layer than I have:

class CustomLayer:
    def __init__(self, x, step, mean, std_dev):
        self.x = x
        self.step = step
        self.mean= mean
        self.std_dev = std_dev
        self.size = len(self.x)
    
    def transform_signal(self, y):
        indices_transform = np.arange(0,len(y), self.step)
        a1 = y[indices_transform]
        a2 = a1[1:]
        a1 = a1[:-1]

        return np.repeat( (a1 + (a2-a1)/2), self.step )

    def gaussian_noise(self):
        return np.random.normal(loc=self.mean, scale=self.std_dev, size=self.size)
    
    def transform(self):
        x_gauss_noise = self.x + self.gaussian_noise()
        return self.transform_signal(y=x_gauss_noise)
    

And below is a small three row example dataset that I have:

arr = np.expand_dims( np.array([ [1, 5, 7, 8, 10, 11, 11.5, 12, 12.5, 13, 13.2, 13.8, 14.3],
                                 [11, 15, 17, 18, 110, 111, 111.5, 112, 112.5, 113, 113.2, 113.8, 114.3],
                                 [2, 6, 8, 9, 11, 12, 12.5, 13, 13.5, 14, 15.2, 14.8, 15.3]]), axis=2 )

Application of the custom layer to the first row will do a transformation like the one shown in the below picture. Here arr[0,:,0] has length=13, and the transformed array, i.e., arr1 has length=12.

test = CustomLayer(x=arr[0,:,0],
             mean=0,
             std_dev=0.03,
             step=2)

arr1 = test.transform()

It is okay if the values of the parameters step, mean and std_dev are set as 2, 0 and 0.03 respectively. But, I would like the CustomLayer to act independently on each row during its operation in the Tensorflow model.

I would like my Tensorflow model to be like the below. I would also like the input_shape in this model to be (13,1) since the length of each row in the array is 13.

import tensorflow as tf

from tensorflow.keras.layers import (Conv1D,
                                     Dense)

model = tf.keras.Sequential([
    CustomLayer(mean=0, std_dev=0.03, step=2),
    Conv1D(filters=2,
           kernel_size=5,
           padding="same",
           activation="relu"),
    Dense(units=1, activation='relu')
])

How can I use the aforementioned CustomLayer in the model specified above as the initial transformation layer?

At present, the above structure of model gives me an error which says:

TypeError                                 Traceback (most recent call last)
Cell In[94], line 2
      1 model = tf.keras.Sequential([
----> 2     CustomLayer(mean=0, std_dev=0.03, step=2),
      3     Conv1D(filters=2,
      4            kernel_size=5,
      5            padding="same",
      6            activation="relu"),
      7     Dense(units=1, activation='relu')
      8 ])
     10 model.summary()

TypeError: CustomLayer.__init__() missing 1 required positional argument: 'x'