Scribd
Upload
19 views

Assignment 6.3

The document loads an image classification model and runs predictions on three images, outputting the top 10 predictions for each image which are a cat, another cat, and a human.

Uploaded by

dash
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
19 views

Assignment 6.3

The document loads an image classification model and runs predictions on three images, outputting the top 10 predictions for each image which are a cat, another cat, and a human.

Uploaded by

dash
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

In 

[1]: import glob, os

import numpy as np

from keras.preprocessing.image import load_img

from keras.preprocessing.image import img_to_array

from keras.applications.resnet50 import preprocess_input

from keras.applications.imagenet_utils import preprocess_input,decode_predictions

import matplotlib.pyplot as plt

from tensorflow.keras.applications import resnet50

resnet_model = resnet50.ResNet50(weights='imagenet')

Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/r


esnet/resnet50_weights_tf_dim_ordering_tf_kernels.h5

102973440/102967424 [==============================] - 153s 1us/step

In [2]: def run_prediction(filename):

input_image = load_img(filename, target_size=(224, 224))

plt.imshow(input_image)

plt.show()

# convert the image to a numpy array

numpy_image = img_to_array(input_image)

image_batch = np.expand_dims(numpy_image,axis=0)

image_procesed= preprocess_input(image_batch)

prediction=resnet_model.predict(image_procesed)

output=filename, decode_predictions(prediction, top=10)

print(output)

with open('Results/predictions/resnet50/results.txt', 'a') as f:

f.writelines(str(output))

In [5]: filename = 'C:/Users/walee/Desktop/Adil Khan/Big Data/DSC 650/Assignments/Assignment


run_prediction(filename)

('C:/Users/walee/Desktop/Adil Khan/Big Data/DSC 650/Assignments/Assignment 06/image


s/cat1.PNG', [[('n02124075', 'Egyptian_cat', 0.40473214), ('n02123045', 'tabby', 0.3
7820032), ('n02123159', 'tiger_cat', 0.18440679), ('n02127052', 'lynx', 0.02030049),
('n02120505', 'grey_fox', 0.0031651843), ('n02356798', 'fox_squirrel', 0.000663975
2), ('n02129604', 'tiger', 0.0004948665), ('n02128757', 'snow_leopard', 0.0004507356
2), ('n03958227', 'plastic_bag', 0.00036802635), ('n02128385', 'leopard', 0.00035691
64)]])

In [6]: filename2 = 'C:/Users/walee/Desktop/Adil Khan/Big Data/DSC 650/Assignments/Assignmen


run_prediction(filename2)

('C:/Users/walee/Desktop/Adil Khan/Big Data/DSC 650/Assignments/Assignment 06/image


s/cat2.PNG', [[('n02123045', 'tabby', 0.6036403), ('n02124075', 'Egyptian_cat', 0.30
550975), ('n02123159', 'tiger_cat', 0.023157293), ('n02127052', 'lynx', 0.00862331
1), ('n04493381', 'tub', 0.005825389), ('n02909870', 'bucket', 0.004084795), ('n0348
2405', 'hamper', 0.003631829), ('n02123394', 'Persian_cat', 0.0030924305), ('n079308
64', 'cup', 0.0030116315), ('n04209239', 'shower_curtain', 0.0025875547)]])

In [8]: filename3 = 'C:/Users/walee/Desktop/Adil Khan/Big Data/DSC 650/Assignments/Assignmen


run_prediction(filename3)

('C:/Users/walee/Desktop/Adil Khan/Big Data/DSC 650/Assignments/Assignment 06/image


s/human.PNG', [[('n03617480', 'kimono', 0.2810746), ('n02963159', 'cardigan', 0.0987
3904), ('n04136333', 'sarong', 0.09751529), ('n03866082', 'overskirt', 0.08254426),
('n03877472', 'pajama', 0.065047406), ('n03450230', 'gown', 0.051486332), ('n0431117
4', 'steel_drum', 0.026140286), ('n04325704', 'stole', 0.014662189), ('n03534580',
'hoopskirt', 0.014379749), ('n02948072', 'candle', 0.013780539)]])

In [ ]:

You might also like