Изображения в папке сравнить с заданным

from sentence_transformers import SentenceTransformer, util
from PIL import Image
import glob
import os
# Load the OpenAI CLIP Model
print('Loading CLIP Model...')
model = SentenceTransformer('clip-ViT-B-32')
# Next we compute the embeddings
# To encode an image, you can use the following code:
# from PIL import Image
# encoded_image = model.encode(Image.open(filepath))
image_names = list(glob.glob('./*.jpg'))
print("Images:", len(image_names))
encoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)
# Now we run the clustering algorithm. This function compares images aganist 
# all other images and returns a list with the pairs that have the highest 
# cosine similarity score
processed_images = util.paraphrase_mining_embeddings(encoded_image)
NUM_SIMILAR_IMAGES = 10 
# =================
# DUPLICATES
# =================
print('Finding duplicate images...')
# Filter list for duplicates. Results are triplets (score, image_id1, image_id2) and is scorted in decreasing order
# A duplicate image will have a score of 1.00
# It may be 0.9999 due to lossy image compression (.jpg)
duplicates = [image for image in processed_images if image[0] >= 0.999]
# Output the top X duplicate images
for score, image_id1, image_id2 in duplicates[0:NUM_SIMILAR_IMAGES]:
    print("\nScore: {:.3f}%".format(score * 100))
    print(image_names[image_id1])
    print(image_names[image_id2])
# =================
# NEAR DUPLICATES
# =================
print('Finding near duplicate images...')
# Use a threshold parameter to identify two images as similar. By setting the threshold lower, 
# you will get larger clusters which have less similar images in it. Threshold 0 - 1.00
# A threshold of 1.00 means the two images are exactly the same. Since we are finding near 
# duplicate images, we can set it at 0.99 or any number 0 < X < 1.00.
threshold = 0.99
near_duplicates = [image for image in processed_images if image[0] < threshold]
for score, image_id1, image_id2 in near_duplicates[0:NUM_SIMILAR_IMAGES]:
    print("\nScore: {:.3f}%".format(score * 100))
    print(image_names[image_id1])
    print(image_names[image_id2])

filename = "massiv_img.txt"
# Открываем файл для чтения
with open(filename, "r") as f:
    # Считываем все строки из файла и сохраняем их в список
    image_names = [line.rstrip() for line in f]

query_image = Image.open('2323.jpg')

image_names = list(glob.glob('./*.jpg'))
print("Images:", len(image_names))
encoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)

filename = "massiv_img.txt"
# Открываем файл для чтения
with open(filename, "r") as f:
    # Считываем все строки из файла и сохраняем их в список
    image_names = [line.rstrip() for line in f]

processed_images = util.paraphrase_mining_embeddings(encoded_image)

processed_images = util.paraphrase_mining_embeddings(encoded_image)

arrfile = ['a','b','c','d']
file = 'z'
for item in arrfile:
    image_names = [file, item]
...

processed_images = util.paraphrase_mining_embeddings(encoded_image)

odin_image = Image.open('2323.jpg')
filename = "massiv_img.txt"
# Открываем файл для чтения
with open(filename, "r") as f:
    # Считываем все строки из файла и сохраняем их в список
    image_names = [line.rstrip() for line in f]

encoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)

filename = "massiv_img.txt"
# Открываем файл для чтения
with open(filename, "r") as f:
# Считываем все строки из файла и сохраняем их в список
    image_names = [line.rstrip() for line in f]
# Добавляем ещё фото
odin_image = Image.open('2323.jpg')
for item in line:
    image_names = [file, item]

encoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)
# Now we run the clustering algorithm. This function compares images aganist 
# all other images and returns a list with the pairs that have the highest 
# cosine similarity score
processed_images = util.paraphrase_mining_embeddings(encoded_image)

filename = "massiv_img.txt"
# Открываем файл для чтения
with open(filename, "r") as f:
    # Считываем все строки из файла и сохраняем их в список
    image_1 = [line.rstrip() for line in f]
 
odin_image = Image.open('2323.jpg')
 
for item in image_1:
    image_names = [odin_image, item]
    ncoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)
    processed_images = util.paraphrase_mining_embeddings(ncoded_image)
    NUM_SIMILAR_IMAGES = 10

 File "img.py", line 28, in <module>
    ncoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)
  File "img.py", line 28, in <listcomp>
    ncoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)
  File "python3.7/site-packages/PIL/Image.py", line 3245, in open
    prefix = fp.read(16)

#здесь все импорты для инициализации
...
# до определения модели:
model = SentenceTransformer('clip-ViT-B-32')
# а далее, уже так:
file = '2323.jpg'
filename = "massiv_img.txt"
with open(filename, "r") as f:
    arrfile = [line.rstrip() for line in f]
for item in arrfile:
    image_names = [file, item]
    encoded_image = model.encode([Image.open(filepath) for filepath in image_names], batch_size=128, convert_to_tensor=True, show_progress_bar=True)
    # здесь весь остальной код для определения дубликатов (т.е. для каждой пары файлов он будет выполняться отдельно)
    ...

 my_array.append(round(score * 100))
#После цикла
# находим максимальное значение
max_num = max(my_array)
# печатаем результат
print(max_num)