Chapter 5: Convolutional Neural Networks for Computer Vision

Activity 5: Making Use of Data Augmentation to Classify correctly Images of Flowers

Solution

1. Open your Google Colab interface.

   Note

   You will need to mount your drive using the Dataset folder, and accordingly set the path to continue ahead.

   import numpyasnp
   classes=['daisy','dandelion','rose','sunflower','tulip']
   X=np.load("Dataset/flowers/%s_x.npy"%(classes[0]))
   y=np.load("Dataset/flowers/%s_y.npy"%(classes[0]))
   print(X.shape)
   forflowerinclasses[1:]:
       X_aux=np.load("Dataset/flowers/%s_x.npy"%(flower))
       y_aux=np.load("Dataset/flowers/%s_y.npy"%(flower))
       print(X_aux.shape)
       X=np.concatenate((X,X_aux),axis=0)
       y=np.concatenate((y,y_aux),axis=0)
       
   print(X.shape)
   print(y.shape)

2. To output some samples from the dataset:

   import random 
   random.seed(42) 
   from matplotlib import pyplot as plt
   import cv2
   
   for idx in range(5): 
       rnd_index = random.randint(0, 4000) 
       plt.subplot(1,5,idx+1),plt.imshow(cv2.cvtColor(X[rnd_index],cv2.COLOR_BGR2RGB)) 
       plt.xticks([]),plt.yticks([])
       plt.savefig("flowers_samples.jpg", bbox_inches='tight')
   plt.show() 

   The output is as follows:

   

   Figure 5.23: Samples from the dataset

3. Now, we will normalize and perform one-hot encoding:

   from keras import utils as np_utils
   X = (X.astype(np.float32))/255.0 
   y = np_utils.to_categorical(y, len(classes))
   print(X.shape)
   print(y.shape)

4. Splitting the training and testing set:

   from sklearn.model_selection import train_test_split
   x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
   input_shape = x_train.shape[1:]
   print(x_train.shape)
   print(y_train.shape)
   print(x_test.shape)
   print(y_test.shape)
   print(input_shape)

5. Import libraries and build the CNN:

   from keras.models import Sequential
   from keras.callbacks import ModelCheckpoint
   from keras.layers import Input, Dense, Dropout, Flatten
   from keras.layers import Conv2D, Activation, BatchNormalization
   def CNN(input_shape):
       model = Sequential()
       
       model.add(Conv2D(32, kernel_size=(5, 5), padding='same',  strides=(2,2), input_shape=input_shape))
       model.add(Activation('relu')) 
       model.add(BatchNormalization()) 
       model.add(Dropout(0.2))
   
       model.add(Conv2D(64, kernel_size=(3, 3), padding='same', strides=(2,2))) 
       model.add(Activation('relu')) 
       model.add(BatchNormalization()) 
       model.add(Dropout(0.2))
   
       model.add(Conv2D(128, kernel_size=(3, 3), padding='same', strides=(2,2))) 
       model.add(Activation('relu')) 
       model.add(BatchNormalization()) 
       model.add(Dropout(0.2))
       
       model.add(Conv2D(256, kernel_size=(3, 3), padding='same', strides=(2,2))) 
       model.add(Activation('relu')) 
       model.add(BatchNormalization()) 
       model.add(Dropout(0.2))
       
       model.add(Flatten())
       model.add(Dense(512))
       model.add(Activation('relu'))
       model.add(BatchNormalization())
       model.add(Dropout(0.5))
       model.add(Dense(5, activation = "softmax"))
   
       return model

6. Declare ImageDataGenerator:

   from keras.preprocessing.image import ImageDataGenerator
   datagen = ImageDataGenerator(
           rotation_range=10,
           zoom_range = 0.2,
           width_shift_range=0.2,
           height_shift_range=0.2,
           shear_range=0.1,
           horizontal_flip=True
           )

7. We will now train the model:

   datagen.fit(x_train)
   
   model = CNN(input_shape)
   
   model.compile(loss='categorical_crossentropy', optimizer='Adadelta', metrics=['accuracy'])
   
   ckpt = ModelCheckpoint('Models/model_flowers.h5', save_best_only=True,monitor='val_loss', mode='min', save_weights_only=False) 
   
   //{…}##the detailed code can be found on Github##
   
   model.fit_generator(datagen.flow(x_train, y_train,
                               batch_size=32),
                       epochs=200,
                       validation_data=(x_test, y_test),
                       callbacks=[ckpt],
                       steps_per_epoch=len(x_train) // 32,
                       workers=4)

8. After which, we will evaluate the model:

   from sklearn import metrics
   model.load_weights('Models/model_flowers.h5')
   y_pred = model.predict(x_test, batch_size=32, verbose=0)
   y_pred = np.argmax(y_pred, axis=1)
   y_test_aux = y_test.copy()
   y_test_pred = list()
   for i in y_test_aux:
       y_test_pred.append(np.argmax(i))
   
   //{…}
   ##the detailed code can be found on Github##
   
   print (y_pred)
   
   # Evaluate the prediction
   accuracy = metrics.accuracy_score(y_test_pred, y_pred)
   print('Acc: %.4f' % accuracy)

9. The accuracy achieved is 91.68%.

10. Try the model with unseen data:

    classes = ['daisy','dandelion','rose','sunflower','tulip']
    images = ['sunflower.jpg','daisy.jpg','rose.jpg','dandelion.jpg','tulip .jpg']
    model.load_weights('Models/model_flowers.h5')
    
    for number in range(len(images)):
        imgLoaded = cv2.imread('Dataset/testing/%s'%(images[number])) 
        img = cv2.resize(imgLoaded, (150, 150)) 
        img = (img.astype(np.float32))/255.0 
        img = img.reshape(1, 150, 150, 3)
        plt.subplot(1,5,number+1),plt.imshow(cv2.cvtColor(imgLoaded,cv2.COLOR_BGR2RGB)) 
        plt.title(np.argmax(model.predict(img)[0])) 
        plt.xticks([]),plt.yticks([]) 
    plt.show()

    Output will look like this:

    

    Figure 5.24: Prediction of roses result from Activity05

    Note

    The detailed code for this activity can be found on GitHub - https://github.com/PacktPublishing/Artificial-Vision-and-Language-Processing-for-Robotics/blob/master/Lesson05/Activity05/Activity05.ipynb