Thanks for the great article with awesome gifs.
In one related code snippet “tf.keras.layers.Conv2D(32, (3,3), padding=’same’, activation=tf.nn.relu, input_shape=(28, 28, 1))”
A Kernel with stride of 3x3 is being used with same padding. However, this layer generates 32 convoluted images? Why is that done here (generating 32 from 1 image) and how?
Distraction-free reading. No ads.
Organize your knowledge with lists and highlights.
Tell your story. Find your audience.
Read member-only stories
Support writers you read most
Earn money for your writing
Listen to audio narrations
Read offline with the Medium app
Writes about tech & entrepreneurship. Founder of 2 tech startups in 2022 & Program manager. Got my hands dirty in things I knew nothing about and made it work.
