Image Classification Using CNN (Dogs vs Cats)¶
Importing required libraries and setting hyperparameters¶
In [1]:
import cv2
import numpy as np
import os
from random import shuffle
from tqdm import tqdm
TRAIN_DIR = 'C:/Python36/ml/kaggle/catvsdog/test'
TEST_DIR = 'C:/Python36/ml/kaggle/catvsdog/train'
IMG_SIZE = 50
LR = 1e-3
MODEL_NAME = 'dogsvscats-{}-{}.model'.format(LR, '6-layer-conv-basic')
Defining label [0,1] for dog and [1,0] for cat¶
In [2]:
def label_img(img):
pet = img.split('.')[-2]
if pet == 'cat': return [1,0]
elif pet == 'dog': return [0,1]
Preparing training data¶
In [3]:
def create_train_data():
training_data = []
for img in tqdm(os.listdir(TRAIN_DIR)):
label = label_img(img)
path = os.path.join(TRAIN_DIR,img)
img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
training_data.append([np.array(img),np.array(label)])
shuffle(training_data)
np.save('train_data.npy', training_data)
return training_data
Preparing testing data¶
In [4]:
def process_test_data():
testing_data = []
for img in tqdm(os.listdir(TEST_DIR)):
path = os.path.join(TEST_DIR,img)
img_num = img.split('.')[0]
img = cv2.imread(path,cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (IMG_SIZE,IMG_SIZE))
testing_data.append([np.array(img), img_num])
shuffle(testing_data)
np.save('test_data.npy', testing_data)
return testing_data
In [5]:
train_data = np.load('train_data.npy')
Defining the CNN model¶
In [6]:
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tensorflow as tf
tf.reset_default_graph()
convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 1], name='input')
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 128, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 64, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = conv_2d(convnet, 32, 5, activation='relu')
convnet = max_pool_2d(convnet, 5)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 2, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
In [7]:
if os.path.exists('{}.meta'.format(MODEL_NAME)):
model.load(MODEL_NAME)
print('model loaded!')
Train the data using CNN¶
In [8]:
train = train_data[:-500]
test = train_data[-500:]
X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
Y = np.array([i[1] for i in train])
test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,1)
test_y = np.array([i[1] for i in test])
model.fit({'input':X}, {'targets': Y}, n_epoch=10, validation_set=({'input':test_x},{'targets':test_y}),snapshot_step=500, show_metric=True, run_id=MODEL_NAME)
In [9]:
model.save(MODEL_NAME)
Predicting and Plotting the results on a graph¶
In [11]:
import matplotlib.pyplot as plt
test_data = process_test_data()
# if you already have some saved:
#test_data = np.load('test_data.npy')
fig=plt.figure()
for num,data in enumerate(test_data[:12]):
# cat: [1,0]
# dog: [0,1]
img_num = data[1]
img_data = data[0]
y = fig.add_subplot(3,4,num+1)
orig = img_data
data = img_data.reshape(IMG_SIZE,IMG_SIZE,1)
model_out = model.predict([data])[0]
if np.argmax(model_out) == 1: str_label='Dog'
else: str_label='Cat'
y.imshow(orig,cmap='gray')
plt.title(str_label)
y.axes.get_xaxis().set_visible(False)
y.axes.get_yaxis().set_visible(False)
plt.show()
