What are kernel initializers in keras?
This recipe explains what are kernel initializers in keras
Recipe Objective
What are kernel initializers in keras?
Kernel initializers are used to statistically initialise the weights in the model. This will generate the weights and distribute them, it can be used as the starting weights
Table of Contents
Step 1- Importing Libraries
import numpy as np
import keras
from keras.models import Sequential
from keras.layers import Activation, Dense
Step 2- Creating a model.
We will create a model with the initializer.
# 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='normal', activation='relu'))
model.summary()
What Users are saying..
Ameeruddin Mohammed
I come from a background in Marketing and Analytics and when I developed an interest in Machine Learning algorithms, I did multiple in-class courses from reputed institutions though I got good... Read More