Project 6 Mini Project

pip install tensorflow                            #install tensor flow


!pip install keras                                 #install keras


import numpy as np                                         #import keras and numpy
import keras
from keras import backend as K
from keras.layers.core import Dense, Activation             #import the activation functions
from keras.optimizers import Adam
from keras.metrics import categorical_crossentropy
from keras.preprocessing.image import ImageDataGenerator
import keras.utils as image
from keras.models import Model                 
from keras.applications import imagenet_utils
from sklearn.metrics import confusion_matrix                     #import confusion matrix
import itertools
import matplotlib.pyplot as plt                       

#call the mobile net architecture from the keras
mobile = keras.applications.mobilenet.MobileNet()                

#prepocessing the image 
def prepare_image(file):  
    #load the file resized to 224,224 as mobilenet standard                                
    img = image.load_img(file, target_size=(224, 224))         
    img_array = image.img_to_array(img)                      
    img_array_expanded_dims = np.expand_dims(img_array, axis=0)                
    return keras.applications.mobilenet.preprocess_input(img_array_expanded_dims)       #return the preprocessed image,scale the image to pixel values


from IPython.display import Image

#display the image to be classified
Image(filename='cat.1181.jpg', width=300,height=200)

#pass the image to the prepare image               
preprocessed_image = prepare_image('cat.1181.jpg') 

#predicts the image
predictions = mobile.predict(preprocessed_image)            

#gives the top 5 predicted results        
results = imagenet_utils.decode_predictions(predictions)           
results


from IPython.display import Image
Image(filename='dog.37.jpg', width=300,height=200)

preprocessed_image = prepare_image('dog.37.jpg')
predictions = mobile.predict(preprocessed_image)
results = imagenet_utils.decode_predictions(predictions)
results