如何在Keras中显示由Resnet50模型提取的图像的特征

Question

So what I am trying to do is display the features that were extracted from a Resnet50 model and saved as a .npy.

I can read it in all and fine and the array looks fine. But I cannot figure out a way to display the results well. How can I show this in matplotlib of opencv ?

Here is what I have so far:

import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
from matplotlib import cm
import os

path = "ResnetFeatures/"

def load_resnet_features(file, path):
    file_path = os.path.join(path, file)
    return np.load(file_path)

test_file = '1500test.npy'




test_feature = load_resnet_features(test_file, path)
print(test_feature.shape)
test_feature = np.squeeze(test_feature, axis=0)
print(test_feature.shape)
test_feature = test_feature.reshape((49, 2048))
plt.imshow(test_feature)
plt.show()

Which gives this

(1, 7, 7, 2048)
(7, 7, 2048)

This gives this, but it is not what I want. I would like something that is more square in shape are the original image is (224,224,3)

Answer 1

Ok I figured it out thanks to Jake P help.

So I know the image can be reshaped like (49, 2048) So I brock apart 2048 to get this (7,7) (64, 32) Then just cross multipled (7*32) (7 * 64)

test_feature = test_feature.reshape((448, 224))
print_shape(test_feature)