training_model_code.py

# -*- coding: utf-8 -*-
"""
Created on Tue May 21 17:23:33 2019

@author: Shahzeb
"""

# Convolutional Neural Network

# Installing Theano
# pip install --upgrade --no-deps git+git://github.com/Theano/Theano.git

# Installing Tensorflow
# pip install tensorflow

# Installing Keras
# pip install --upgrade keras

#Installing pillow
#pip install pillow

# Part 1 - Building the CNN

# Importing the Keras libraries and packages
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.models import model_from_json

# Initialising the CNN
classifier = Sequential()

# Step 1 - Convolution
classifier.add(Conv2D(64, (4, 4), input_shape = (299, 299, 3), activation = 'relu'))

# Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size = (4, 4)))

# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))
classifier.add(Conv2D(16, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (3, 3)))

# Step 3 - Flattening
classifier.add(Flatten())

# Step 4 - Full connection
classifier.add(Dense(units = 40, activation = 'relu'))
classifier.add(Dense(units = 10, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))

# Compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

# Part 2 - Fitting the CNN to the images

from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

test_datagen = ImageDataGenerator(rescale = 1./255)

training_set = train_datagen.flow_from_directory('dataset/model_1/trn_set',
                                                 target_size = (299, 299),
                                                 batch_size = 10,
                                                 class_mode = 'binary')

test_set = test_datagen.flow_from_directory('dataset/model_1/tst_set',
                                            target_size = (299, 299),
                                            batch_size = 10,
                                            class_mode = 'binary')

classifier.fit_generator(training_set,
                         steps_per_epoch = 3000,
                         epochs = 3,
                         validation_data = test_set,
                         validation_steps = 600)

# serialize model to JSON
model_json = classifier.to_json()
with open("models/model_1.json", "w") as json_file:
    json_file.write(model_json)
# serialize weights to HDF5
classifier.save_weights("models/model_1.h5")
print("Saved model to disk")