In this recipe, we will show you to classify objects in using a CNN. We will train the network from scratch to classify five different flower types in images. The images have different sizes. For this recipe, we will be using Keras.
- Create a new Python file and import the necessary libraries:
import numpy as np import glob import cv2 import matplotlib.pyplot as plt from sklearn.preprocessing import LabelBinarizer from sklearn.model_selection import train_test_split from sklearn.metrics import accuracy_score import keras from keras.models import Sequential, load_model from keras.layers import Dense, Dropout, Activation, Flatten, Conv2D, MaxPooling2D, Lambda, Cropping2D from keras.utils import np_utils from keras import optimizers SEED = 2017
- Next, we load the dataset and extract the labels:
# Specify data directory and extract all file names DATA_DIR = '../Data/' images = glob.glob(DATA_DIR + "flower_photos/*/*.jpg") # Extract labels from file...