Project 10: Custom Price Scaler Layer
ML Engineer
Builds on these lessons
Current Task
Objective
Subclassing layers.Layer and implementing call() lets you define custom computation Keras doesn't already provide as a built-in layer.
Task: write a PriceScaler custom layer that multiplies its input by a factor, and print the scaled result.
index.py
import tensorflow as tf
from tensorflow.keras import layers
class PriceScaler(layers.Layer):
def __init__(self, factor):
super().__init__()
self.factor = factor
def call(self, inputs):
return inputs * self.factor
scaler = PriceScaler(1000.0)
print(scaler(tf.constant([250.0, 340.0])).numpy())
* Hint: Correct characters turn green, incorrect ones turn red.
Live Preview
🖼️
Verify your code to see the preview