
Exploring Deep Learning Models: Comparing ANN vs CNN for Image Recognition
Author(s): SETIA BUDI SUMANDRA
Originally published on Towards AI.
Have you ever wondered how well Artificial Neural Networks (ANN) perform compared to Convolutional Neural Networks (CNN) in classifying images?
In this article, Iβll walk you through a hands-on project where we train both ANN and CNN models using the CIFAR-10 dataset and build a fun interactive prediction UI that lets you upload your own images and see how each model performs in real-time!
Letβs break it all down line by line, block by block, with enough clear explanations.
import numpy as npimport matplotlib.pyplot as pltimport seaborn as snsfrom tensorflow.keras import layers, modelsfrom tensorflow.keras.datasets import cifar10import ipywidgets as widgetsfrom IPython.display import display, clear_outputfrom PIL import Imageimport io,osfrom IPython.display import display, clear_outputimport ipywidgets as widgetsfrom ipywidgets import Layoutfrom collections import OrderedDict
Loads essential packages for:
Data manipulation: numpyVisualization: matplotlib & seabornDataset and building/training models: tensorflow.kerasUI interaction: ipywidgets, IPython.displayImage processing: PIL(X_train, y_train), (X_test, y_test) = cifar10.load_data()# NormalisasiX_train, X_test = X_train / 255.0, X_test / 255.0# Label reshapey_train = y_train.flatten()y_test = y_test.flatten()Loads CIFAR-10, a dataset of 60,000 32×32 color images from 10 categories.Normalizes the pixel values from [0β255] to [0β1].Flattens the label arrays to 1D for compatibility with model training.class_names = ['Airplane', 'Automobile', 'Bird', 'Cat', 'Deer', 'Dog', 'Frog', 'Horse', 'Ship', 'Truck']
It provides human-readable names for the 10… Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming aΒ sponsor.
Published via Towards AI