Explain with an example how He_normal initializer works in keras
This recipe explains with an example how He_normal initializer works in keras
Recipe Objective
He_Normal initializer
He_Normal initializer takes samples from a truncated normal distribution centered on 0 with stddev = sqrt(2 / fan_in) where fan_in is the number of input units in the weight tensor.
Table of Contents
Step 1- Importing Libraries
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Activation, Dense
import tensorflow as tf
Step-2 Initializing the He_normal initializers.
We show you two ways to initialize the He_normal initializers.
initializer = tf.keras.initializers.HeNormal()
values = initializer(shape=(2, 2))
layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)
Step 3- We will create the model
We will be reshaping and creating the model
# define input data
X = np.array([17, 35, 400, 230])
# show input data for context
print(X)
# reshape input data into one sample a sample with a channel
X = X.reshape((1, 2, 2, 1))
# define model
model = Sequential()
model.add(Dense(13, input_dim=13, kernel_initializer=initializer, activation='relu'))
model.summary()
What Users are saying..
Gautam Vermani
Having worked in the field of Data Science, I wanted to explore how I can implement projects in other domains, So I thought of connecting with ProjectPro. A project that helped me absorb this topic... Read More