Image Classification with ANN | Data Science | Machine Learning

First, we need to load a dataset. In this Image Classification model we will tackle Fashion MNIST. It has a format of 60,000 grayscale images of 28 x 28 pixels each, with 10 classes. Let’s import some necessary libraries to start with this task:

# Python ≥3.5 is required
import sys
assert sys.version_info >= (3, 5)

# Scikit-Learn ≥0.20 is required
import sklearn
assert sklearn.__version__ >= "0.20"

try:
    # %tensorflow_version only exists in Colab.
    %tensorflow_version 2.x
except Exception:
    pass

# TensorFlow ≥2.0 is required
import tensorflow as tf
assert tf.__version__ >= "2.0"

# Common imports
import numpy as np
import os

# to make this notebook's output stable across runs
np.random.seed(42)

# To plot pretty figures
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)

Using Keras to Load the Dataset

Keras provide some quality functions to fetch and load common datasets, including MNIST, Fashion MNIST, and the California housing dataset. Let’s start by loading the fashion MNIST dataset to create an Image Classification model. Keras has a number of functions to load popular datasets in keras.datasets. The dataset is already split for you between a training set and a test set, but it can be useful to split the training set further to have a validation set:

import tensorflow as tf
from tensorflow import keras
fashion_mnist = keras.datasets.fashion_mnist
(X_train_full, y_train_full), (X_test, y_test) = fashion_mnist.load_data()

When loading MNIST or Fashion MNIST using Keras rather than Scikit-Learn, one important difference is that every image is represented as a 28 x 28 array rather than a 1D array of size 784. Moreover, the pixel intensities are represented as integers rather than the floats. Let’s take a look at the shape and data type of the training set:

X_train_full.shape

(60000, 28, 28)

X_train_full.dtype

dtype(‘uint8’)

Note that the dataset is already split into a training set and a test set, but there is no validation set, so we’ll create one now. Additionally, since we are going to train the ANN using Gradient Descent, we must scale the input features. For simplicity, I will scale the pixel intensities down to the 0-1 range by dividing them by 255.0:

X_valid, X_train = X_train_full[:5000] / 255., X_train_full[5000:] / 255.
y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
X_test = X_test / 255.

You can plot an image using Matplotlib’s imshow() function, with a 'binary' color map:

plt.imshow(X_train[0], cmap="binary")
plt.axis('off')
plt.show()

#by aman kharwal #ann #data science #deep learning #machine learning #neural networks

Using Keras to Load the Dataset

thecleverprogrammer.com

Image Classification with ANN | Data Science | Machine Learning | Python