python - resizing images from 64x64 to 224x224 for the VGG model

Question

Can we resize an image from 64x64 to 256x256 without affecting the resolution is that a way to add zero on new row and column in the new resized output I m working on vgg and I get an error while adding my 64x64 input image because vggface is a pertrained model that include an input size of 224

code:

from keras.models import Model, Sequential
from keras.layers import Input, Convolution2D, ZeroPadding2D, MaxPooling2D, Flatten, Dense, Dropout, Activation
from PIL import Image
import numpy as np
from keras.preprocessing.image import load_img, save_img, img_to_array
from keras.applications.imagenet_utils import preprocess_input
from keras.preprocessing import image
import matplotlib

matplotlib.use('TkAgg')

import matplotlib.pyplot as plt

# from sup5 import X_test, Y_test
from sklearn.metrics import roc_curve, auc


from keras.models import Model, Sequential
from keras.layers import Input, Convolution2D, ZeroPadding2D, MaxPooling2D, Flatten, Dense, Dropout, Activation
from PIL import Image
import numpy as np
from keras.preprocessing.image import load_img, save_img, img_to_array
from keras.applications.imagenet_utils import preprocess_input
from keras.preprocessing import image
import matplotlib.pyplot as plt

# from sup5 import X_test, Y_test
from sklearn.metrics import roc_curve, auc
from keras.applications.vgg16 import VGG16
from keras.preprocessing import image
from keras.applications.vgg16 import preprocess_input
import numpy as np

model = VGG16(weights='imagenet', include_top=False)




from keras.models import model_from_json




vgg_face_descriptor = Model(inputs=model.layers[0].input
                            , outputs=model.layers[-2].output)
# import  pandas as pd
# test_x_predictions = deep.predict(X_test)
# mse = np.mean(np.power(X_test - test_x_predictions, 2), axis=1)
# error_df = pd.DataFrame({'Reconstruction_error': mse,
#                         'True_class': Y_test})
# error_df.describe()
from PIL import Image


def preprocess_image(image_path):
    img = load_img(image_path, target_size=(224, 224))

    img = img_to_array(img)
    img = np.expand_dims(img, axis=0)

    img = preprocess_input(img)
    return img


def findCosineSimilarity(source_representation, test_representation):
    a = np.matmul(np.transpose(source_representation), test_representation)
    b = np.sum(np.multiply(source_representation, source_representation))
    c = np.sum(np.multiply(test_representation, test_representation))
    return 1 - (a / (np.sqrt(b) * np.sqrt(c)))


def findEuclideanDistance(source_representation, test_representation):
    euclidean_distance = source_representation - test_representation
    euclidean_distance = np.sum(np.multiply(euclidean_distance, euclidean_distance))
    euclidean_distance = np.sqrt(euclidean_distance)
    return euclidean_distance


vgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output)

# for encod epsilon = 0.004
epsilon = 0.16
# epsilon = 0.095
retFalse,ret_val, euclidean_distance = verifyFace(str(i)+"test.jpg", str(j)+"train.jpg", epsilon)
  verifyFace1(str(i) + "testencod.jpg", str(j) + "trainencod.jpg")

Error : ValueError: operands could not be broadcast together with remapped shapes [original->remapped]: (512,14,14)->(512,newaxis,newaxis) (14,14,512)->(14,newaxis,newaxis) and requested shape (14,512)

Answer 1

I'm not sure what you mean, here is my solution for you. First method, if i understand clearly what you mean, for adding pad with zero value you need to use numpy.pad for each layer of image.

I use this image for take example, its shape is 158x84x3

import numpy as np
import cv2
from matplotlib import pyplot as mlt
image = cv2.imread('zero.png')
shape = image.shape
add_x = int((256-shape[0])/2)
add_y = int((256-shape[1])/2)
temp_img = np.zeros((256,256,3),dtype = int)
for i in range(3):
    temp_img[:,:,i] = np.pad(image[:,:,i],((add_x,add_x),(add_y,add_y)),'constant', constant_values = (0))
mlt.imshow(temp_img)

By this code i can add padding into picture and have the result like this.

Now its shape is 256x256x3 like you want. Or another method for you is use Image of Pillow library. By using that, you can resize the picture without losing too much information with very simple code.

from PIL import Image
image = Image.fromarray(image)
img = image.resize((256, 256), Image.BILINEAR) 
mlt.imshow(img)

That code will give you this solution

Hope my answer can help you solve the problem!