COVID19_Detector.py

# -*- coding: utf-8 -*-
"""COVID-19 Detector

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/github/dgeorge1000/COVID-19-CNN-Image-Detection-from-Lung-X-Rays/blob/main/COVID19_Detector.ipynb
"""

# Dataset #1: http://cb.lk/covid_19
# Dataset #2: https://www.dropbox.com/sh/7hrnecm53hk0ih3/AABsfKTooQP0Tc3QddOQAfZJa?dl=0

# download the dataset from the Dropbox link
!wget http://cb.lk/covid_19

# unzip the folder to get each image for local access
!unzip covid_19

# paths for both the training dataset and the validation set
# training will be used for the CNN to learn how to differentiate between COVID and non COVID lung images
# validation will be used to test the CNN on data not seen to see its accuracy
TRAIN_PATH = "CovidDataset/Train"
VAL_PATH = "CovidDataset/Val"

# various libraries and imports needed
import numpy as np
import matplotlib.pyplot as plt
import keras
from keras.layers import *
from keras.models import * 
from keras.preprocessing import image

# CNN Based Model using Keras

model = Sequential()
model.add(Conv2D(32,kernel_size=(3,3),activation='relu',input_shape=(224,224,3)))
model.add(Conv2D(64,(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Conv2D(64,(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Conv2D(128,(3,3),activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(64,activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1,activation='sigmoid'))

model.compile(loss=keras.losses.binary_crossentropy,optimizer='adam',metrics=['accuracy'])

# get the general information about the CNN created
model.summary()

# Train from scratch
train_datagen = image.ImageDataGenerator(
    rescale = 1./255,
    shear_range = 0.2,
    zoom_range = 0.2,
    horizontal_flip = True,
)

test_dataset = image.ImageDataGenerator(rescale=1./255)

# using generator saves memory
train_generator = train_datagen.flow_from_directory(
    'CovidDataset/Train',
    target_size = (224,224),
    batch_size = 32,
    class_mode = 'binary')

# 2 classifications
train_generator.class_indices

validation_generator = test_dataset.flow_from_directory(
    'CovidDataset/Val',
    target_size = (224,224),
    batch_size = 32,
    class_mode = 'binary')

# CNN will begin training and testing on the given data
# "accuracy" and "val_accuracy" will show how accurate the CNN is
hist = model.fit_generator(
    train_generator,
    steps_per_epoch=5,
    epochs = 8,
    validation_data = validation_generator,
    validation_steps=2
)