Python Assignment Solution: Implementing Max Pooling Program

Instructions

Objective

Write a python assignment program to implement max pooling.

Requirements and Specifications

Source Code

import numpy as np import tensorflow as tf import pandas as pd import tarfile from PIL import Image from sklearn.model_selection import train_test_split import matplotlib.pyplot as plt from tensorflow.keras.preprocessing.image import ImageDataGenerator import os import cv2 ### Download Dataset Dataset available at: https://www.robots.ox.ac.uk/~vgg/data/flowers/17/17flowers.tgz !wget https://www.robots.ox.ac.uk/~vgg/data/flowers/17/17flowers.tgz !tar -xvf /content/17flowers.tgz ### Load images into NumPy Arrays and label them The dataset contains 80 images per class, and 17 classes. But since we only need 5 classes, we will import only the first 5*80 = 400 images X = [] y = [] j = 0 for i in range(1,80*5+1): # a total of 80*5 images file_dir = f"/content/jpg/image_{str(i).zfill(4)}.jpg" img = Image.open(file_dir).resize((224,224)) # resize to 224x224 img = np.asarray(img, dtype='float32') X.append(img) y.append(j) if i%80 == 0: j += 1 X = np.asarray(X) y = np.asarray(y).reshape(80*5,1) ### Split into train and test test_size = 0.3 # select a 30% for test and 70% for train X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = test_size, random_state = 42) ### Plot first 5 training images plt.figure(figsize = (10,10)) for i in range(16): plt.subplot(4,4,i+1) plt.xticks([]) plt.yticks([]) plt.grid(False) plt.imshow(X_train[i]/255, cmap = plt.cm.binary) plt.xlabel(y_train[i]) # Model 2 model2 = tf.keras.models.Sequential() # Data Augmentation layers model2.add(tf.keras.layers.Rescaling(1./255)) model2.add(tf.keras.layers.RandomFlip("horizontal_and_vertical")) model2.add(tf.keras.layers.RandomRotation(0.5)) # Rest model2.add(tf.keras.layers.Conv2D(16, (3,3), input_shape = (224,224,3), activation='relu')) model2.add(tf.keras.layers.MaxPooling2D(2,2)) model2.add(tf.keras.layers.Conv2D(32, (3,3), activation='relu')) model2.add(tf.keras.layers.MaxPooling2D(2,2)) model2.add(tf.keras.layers.Conv2D(64, (3,3), activation='relu')) model2.add(tf.keras.layers.MaxPooling2D(2,2)) model2.add(tf.keras.layers.Flatten()) model2.add(tf.keras.layers.Dense(128, activation='relu')) # Dropout layer model2.add(tf.keras.layers.Dropout(0.25)) model2.add(tf.keras.layers.Dense(17, activation='softmax')) model2.compile(optimizer='rmsprop', loss = 'sparse_categorical_crossentropy', metrics=['accuracy']) history2 = model2.fit(X_train, y_train, epochs = 100) plt.figure() plt.plot(history2.history['accuracy'], label = 'accuracy') plt.grid(True) plt.xlabel('Epochs') plt.ylabel('Accuracy') plt.show() This one looks way better than the first one, and it is because of the Data Augmentation layers plus the Dropout layer