Deep Learning 3-Classification with Data Augmentation

Learn A-Z Deep Learning in 15 Days

In this Lecture, will learn about Classification with Data Augmentation

What is Data Augmentation?

Data augmentation is the process of increasing the amount and diversity of data. We do not collect new data, rather we transform the already present data. Data augmentation techniques such as Rotation, Shearing, Zooming, Cropping, Flipping, and Changing the brightness level are commonly used to train large neural networks.

Imp:-Use Kaggle Kernel to Run Code. Download the Cat Vs Dog dataset from the link below.

https://drive.google.com/open?id=1UA0NaL8bJqGBqMSeOfbE7FXRZ5z3RV2s

import cv2
import os 
import numpy as np

Unzip  the Dataset

!unzip ../input/train.zip

!unzip ../input/test1.zip

Import the Train 

IMAGE_WIDTH = 128
IMAGE_HEIGHT = 128
IMAGE_CHANNELS = 1
IMAGE_SIZE=(IMAGE_WIDTH, IMAGE_HEIGHT)

directory = "/kaggle/working/train"
data = []
label = []

for filename in os.listdir(directory):

    image = cv2.imread(directory+r'/'+filename,0)
    
    if image is None:
        continue
    image = cv2.resize(image,IMAGE_SIZE)
    
    category = filename.split('.')[0]
    if category == 'dog':
        label.append(1)
    else:
        label.append(0)

    data.append(image/255)

List to Array Conversion

data=np.array(data)
data=data.reshape((data.shape)[0],(data.shape)[1],(data.shape)[2],1)
label=np.array(label)
print(data.shape)
print(label.shape)

Train Test Split

from sklearn.model_selection import train_test_split
x_train, x_val, y_train, y_val = train_test_split(data, label, test_size=0.3, random_state=42) 

One hot encoding

from keras.utils import np_utils
y_train = np_utils.to_categorical(y_train,num_classes=2)
y_val = np_utils.to_categorical(y_val,num_classes=2)

Data Augmentation

from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator( 
                                    rotation_range=20,
                                    width_shift_range=0.2,
                                    height_shift_range=0.2,
                                    brightness_range=(0.3, 0.7),
                                    zoom_range=[0.5, 1.5],
                                    horizontal_flip=True
                                  )

validation_datagen = ImageDataGenerator()
train_generator = train_datagen.flow(x_train, y_train, batch_size = 64)
validation_generator = validation_datagen.flow(x_val, y_val, batch_size= 64)

​CNN Architecture

from keras.models import Sequential, Model
from keras.layers import Dense, Flatten, Activation, Dropout, Conv2D, MaxPooling2D, AveragePooling2D, Input, BatchNormalization
from keras.preprocessing.image import ImageDataGenerator
from keras import optimizers 


img_input  = Input(shape=(IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_CHANNELS))

x = Conv2D(32, (3, 3),activation='relu',padding='same')(img_input)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2))(x)
x = Dropout(0.25)(x)

x = Conv2D(64, (3, 3),activation='relu',padding='same')(img_input)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2))(x)
x = Dropout(0.25)(x)

x = Conv2D(128, (3, 3),activation='relu',padding='same')(img_input)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2))(x)
x = Dropout(0.25)(x)

x = Flatten()(x)
x = Dense(512, activation='relu')(x)
x = Dropout(0.5)(x)
x = Dense(2, activation='softmax', name='predictions')(x)

model = Model(img_input , x)
model.summary()
model.compile(loss='categorical_crossentropy',optimizer=optimizers.adam(lr=1e-6),metrics=['acc'])

Callbacks

from keras.callbacks import ModelCheckpoint, EarlyStopping
​
filepath = "./cp-{epoch:02d}.h5"
​
checkpoint = ModelCheckpoint(filepath,
                             monitor="val_loss",
                             mode="min",
                             save_best_only = True,
                             verbose=1)
​
​
earlystop = EarlyStopping(monitor = 'val_loss', 
                          min_delta = 0, 
                          patience =4,
                          verbose = 1,
                          restore_best_weights = True)
​
# put our call backs into a callback list
callbacks = [earlystop, checkpoint]

Start the Training

model.fit_generator(train_generator,steps_per_epoch = train_generator.n// train_generator.batch_size, epochs=50, validation_data = validation_generator, validation_steps = validation_generator.n// validation_generator.batch_size,  verbose=1, callbacks = callbacks)

Visualize Graph

### Graph Epoch vs acc AND Epoch vs Loss

import matplotlib.pyplot as plt
​
acc = model.history.history['acc']
val_acc = model.history.history['val_acc']
loss = model.history.history['loss']
val_loss = model.history.history['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'blue', label='Training acc')
plt.plot(epochs, val_acc, 'red', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()
plt.figure()
plt.plot(epochs, loss, 'blue', label='Training loss')
plt.plot(epochs, val_loss, 'red', label='Validation loss')
plt.title('Training and validation loss')
plt.legend()
plt.show()

Import test dataset

IMAGE_WIDTH = 128
IMAGE_HEIGHT = 128
IMAGE_CHANNELS = 1
IMAGE_SIZE=(IMAGE_WIDTH, IMAGE_HEIGHT)
​
directory = "/kaggle/working/test1"
data = []
​
​
for filename in os.listdir(directory):
​
    image = cv2.imread(directory+r'/'+filename,0)
    if image is None:
        continue
    image = cv2.resize(image,IMAGE_SIZE)
    
    data.append(image/255)

List to Array Conversion

data = np.array(data)
test_image = np.array(data.reshape((data.shape)[0],(data.shape)[1],(data.shape)[2],1))

Make the Prediction

predictions = model.predict(test_image)
results = np.argmax(predictions, axis = 1)

Convert the label into the category

key={0:'cat',1:'dog'}

label_prediction=[key[r] for r in results]

Display the Result

import matplotlib.image as img
import matplotlib.pyplot as plt
​
nb_rows = 3
nb_cols = 3
fig, axs = plt.subplots(nb_rows, nb_cols, figsize=(6, 6), dpi =100)
​
n = 0
for i in range(0, nb_rows):
    for j in range(0, nb_cols):
        axs[i,j].set_title(label_prediction[n])
        axs[i,j].imshow(data[n],cmap = "gray")
        n += 1  
        
plt.tight_layout()
plt.show()

Create the Dataframe

import pandas as pd
​
df=pd.DataFrame(data={'imagename':os.listdir(directory), 'predicted_labels': label_prediction})
df.head()

Save the dataframe in csv format

df.to_csv('submission_new_model.csv', index=False, header=True)

In the next blog, we will start  Deep Learning Classification with Transfer Learning.

https://sngurukuls247.blogspot.com/2020/05/deep-learning-4-classificationwithtrans.html

                                                                                                                                                    

Follow the link below to access Free Python Lectures-

https://www.youtube.com/sngurukul

Instagram-

https://www.instagram.com/python.india/

Feel free contact me on-

Email - sn.gurukul24.7uk@gmail.com