RGB-PCA在图像上的实现

Question

我想实现PCA（主成分分析）以在图像上获得RGB版本。我正在打开github存储库中的图像。我在这里发现了一个非常有用的类似问题（Reverse generation of RGB PCA image not working） 并实施它，进行正确的纠正，但仍会出现错误：

line 22, in <module>
    img_reshaped = np.reshape(img, (img.shape[0] * img.shape[1], img.shape[2]))
AttributeError: 'JpegImageFile' object has no attribute 'shape'

这是我的密码：

from PIL import Image
import requests
from io import BytesIO
import pylab as plt
import numpy as np

#url = 'https://raw.githubusercontent.com/TeoOG/Computer_Vision_Assistance/master/images/image1.jpg'
url = 'https://raw.githubusercontent.com/TeoOG/Computer_Vision_Assistance/master/images/image2.jpg'
# url = 'https://raw.githubusercontent.com/TeoOG/Computer_Vision_Assistance/master/images/image3.jpg'
# url = 'https://raw.githubusercontent.com/TeoOG/Computer_Vision_Assistance/master/images/image4.jpg'
# url = 'https://raw.githubusercontent.com/TeoOG/Computer_Vision_Assistance/master/images/image5.jpg'

response = requests.get(url)
img = Image.open(BytesIO(response.content))



plt.axis('off')
plt.imshow(img)
img.show()

img_reshaped = np.reshape(img, (img.shape[0] * img.shape[1], img.shape[2]))
print(img_reshaped.shape)

from sklearn.decomposition import PCA

pca = PCA(n_components=3)
pca.fit(img_reshaped)

img_transformed = pca.transform(img_reshaped)
print(img_transformed.shape)

img_inverse = pca.inverse_transform(img_transformed)
print(img_inverse.shape)

plt.imshow(img_inverse)
plt.show()

img_inverse_reshaped = np.reshape(img_inverse, img.shape)

print(img_inverse.shape)

plt.axis('off')
plt.imshow(img_inverse_reshaped)
plt.show()