Convolution Neural Network in Keras

This kernel is created form scratch and will show how to build CNN.

Content

Data Preprocessing
Data Spliting
Building CNN classifier
Training Classiifer
Visualization
Future Work

Importing Required Module

import cv2                                         # working with, mainly resizing, images
import numpy as np                                 # dealing with arrays
import os                                          # dealing with directories
from random import shuffle                         # mixing up or currently ordered data that might lead our network astray in training.
from keras.models import Sequential                # creating sequential model of CNN
from keras.layers import Convolution2D             # creating convolution layer
from keras.layers import MaxPooling2D              # creating maxpool layer
from keras.layers import Flatten                   # creating input vector for dense layer
from keras.layers import Dense                     # create dense layer or fully connected layer
from keras.layers import Dropout                   # use to avoid overfitting by droping some parameters
from keras.preprocessing import image              # generate image
import matplotlib.pyplot as plt                    # use for visualization
import warnings#
warnings.filterwarnings('ignore')
import os
print(os.listdir("../input"))

Using TensorFlow backend.

['cat-and-dog']

Defining training and testing directory.
Defining Image Size.