将 VGG 模型的图像大小从 64x64 调整为 224x224

Question

我们能否在不影响分辨率的情况下将图像大小从 64x64 调整为 256x256 是一种在新调整大小的输出中在新行和新列上添加零的方法我正在处理 vgg，在添加 64x64 输入图像时出现错误，因为 vggface 是包含输入大小 224 的预训练模型

代码：

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")

错误：ValueError：操作数无法与重新映射的形状一起广播[原始->重新映射]：（512,14,14）->（512，newaxis，newaxis）（14,14,512）->（14，newaxis，newaxis）和要求的形状 (14,512)

Answer 1

我不确定你的意思，这是我为你提供的解决方案。第一种方法，如果我清楚地理解你的意思，为了添加零值的 pad，你需要对每一层图像使用 numpy.pad 。

我用这张图片为例，它的形状是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)

通过这段代码，我可以将填充添加到图片中并得到如下结果。

现在它的形状是你想要的 256x256x3 。或者另一种方法是使用枕头库的图像。通过使用它，您可以使用非常简单的代码调整图片大小，而不会丢失太多信息。

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

该代码将为您提供此解决方案

希望我的回答能够帮助您解决问题！