图像相似度比较之 CLIP or DINOv2

#Start by setting up a virtual environment
virtualenv venv-similarity
source venv-similarity/bin/activate
#Install required packages
pip install transformers Pillow torch

import torch
from PIL import Image
from transformers import AutoProcessor, CLIPModel
import torch.nn as nn
device = torch.device('cuda' if torch.cuda.is可用 else "cpu")
processor = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")
model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(device)
#Extract features from image1
image1 = Image.open('img1.jpg')
with torch.no_grad():
    inputs1 = processor(images=image1, return_tensors="pt").to(device)
    image_features1 = model.get_image_features(**inputs1)
#Extract features from image2
image2 = Image.open('img2.jpg')
with torch.no_grad():
    inputs2 = processor(images=image2, return_tensors="pt").to(device)
    image_features2 = model.get_image_features(**inputs2)
#Compute their cosine similarity and convert it into a score between 0 and 1
cos = nn.CosineSimilarity(dim=0)
sim = cos(image_features1[0],image_features2[0]).item()
sim = (sim+1)/2
print('Similarity:', sim)

from transformers import AutoImageProcessor, AutoModel
from PIL import Image
import torch.nn as nn
device = torch.device('cuda' if torch.cuda.is_available() else "cpu")
processor = AutoImageProcessor.from_pretrained('facebook/dinov2-base')
model = AutoModel.from_pretrained('facebook/dinov2-base').to(device)
image1 = Image.open('img1.jpg')
with torch.no_grad():
    inputs1 = processor(images=image1, return_tensors="pt").to(device)
    outputs1 = model(**inputs1)
    image_features1 = outputs1.last_hidden_state
    image_features1 = image_features1.mean(dim=1)
image2 = Image.open('img2.jpg')
with torch.no_grad():
    inputs2 = processor(images=image2, return_tensors="pt").to(device)
    outputs2 = model(**inputs2)
    image_features2 = outputs2.last_hidden_state
    image_features2 = image_features2.mean(dim=1)
cos = nn.CosineSimilarity(dim=0)
sim = cos(image_features1[0],image_features2[0]).item()
sim = (sim+1)/2
print('Similarity:', sim)

import torch
from PIL import Image
from transformers import AutoProcessor, CLIPModel, AutoImageProcessor, AutoModel
import faiss
import os
import numpy as np
device = torch.device('cuda' if torch.cuda.is_available() else "cpu")
#Load CLIP model and processor
processor_clip = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")
model_clip = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(device)
#Load DINOv2 model and processor
processor_dino = AutoImageProcessor.from_pretrained('facebook/dinov2-base')
model_dino = AutoModel.from_pretrained('facebook/dinov2-base').to(device)
#Retrieve all filenames
images = []
for root, dirs, files in os.walk('./val2017/'):
    for file in files:
        if file.endswith('jpg'):
            images.append(root  + '/'+ file)
#Define a function that normalizes embeddings and add them to the index
def add_vector_to_index(embedding, index):
    #convert embedding to numpy
    vector = embedding.detach().cpu().numpy()
    #Convert to float32 numpy
    vector = np.float32(vector)
    #Normalize vector: important to avoid wrong results when searching
    faiss.normalize_L2(vector)
    #Add to index
    index.add(vector)
def extract_features_clip(image):
    with torch.no_grad():
        inputs = processor_clip(images=image, return_tensors="pt").to(device)
        image_features = model_clip.get_image_features(**inputs)
        return image_features
def extract_features_dino(image):
    with torch.no_grad():
        inputs = processor_dino(images=image, return_tensors="pt").to(device)
        outputs = model_dino(**inputs)
        image_features = outputs.last_hidden_state
        return image_features.mean(dim=1)
#Create 2 indexes.
index_clip = faiss.IndexFlatL2(512)
index_dino = faiss.IndexFlatL2(768)
#Iterate over the dataset to extract features X2 and store features in indexes
for image_path in images:
    img = Image.open(image_path).convert('RGB')
    clip_features = extract_features_clip(img)
    add_vector_to_index(clip_features,index_clip)
    dino_features = extract_features_dino(img)
    add_vector_to_index(dino_features,index_dino)
#store the indexes locally
faiss.write_index(index_clip,"clip.index")
faiss.write_index(index_dino,"dino.index")

import faiss
import numpy as np
import torch
from transformers import AutoImageProcessor, AutoModel, AutoProcessor, CLIPModel
from PIL import Image
import os
#Input image
source='laptop.jpg'
image = Image.open(source)
device = torch.device('cuda' if torch.cuda.is_available() else "cpu")
#Load model and processor DINOv2 and CLIP
processor_clip = AutoProcessor.from_pretrained("openai/clip-vit-base-patch32")
model_clip = CLIPModel.from_pretrained("openai/clip-vit-base-patch32").to(device)
processor_dino = AutoImageProcessor.from_pretrained('facebook/dinov2-base')
model_dino = AutoModel.from_pretrained('facebook/dinov2-base').to(device)
#Extract features for CLIP
with torch.no_grad():
    inputs_clip = processor_clip(images=image, return_tensors="pt").to(device)
    image_features_clip = model_clip.get_image_features(**inputs_clip)
#Extract features for DINOv2
with torch.no_grad():
    inputs_dino = processor_dino(images=image, return_tensors="pt").to(device)
    outputs_dino = model_dino(**inputs_dino)
    image_features_dino = outputs_dino.last_hidden_state
    image_features_dino = image_features_dino.mean(dim=1)
def normalizeL2(embeddings):
    vector = embeddings.detach().cpu().numpy()
    vector = np.float32(vector)
    faiss.normalize_L2(vector)
    return vector
image_features_dino = normalizeL2(image_features_dino)
image_features_clip = normalizeL2(image_features_clip)
#Search the top 5 images
index_clip = faiss.read_index("clip.index")
index_dino = faiss.read_index("dino.index")
#Get distance and indexes of images associated
d_dino,i_dino = index_dino.search(image_features_dino,5)
d_clip,i_clip = index_clip.search(image_features_clip,5)