目录
安装 测试成功：
-
CPU version conda install -c conda-forge faiss-cpu
-
GPU version：conda install -c conda-forge faiss-gpu
pip安装 测试失败：
cpu版：
pip --default-time=1000 install -i https://pypi.tuna.tsinghua.edu.cn/simple faiss
gpu版：
pip --default-time=1000 install -i https://pypi.tuna.tsinghua.edu.cn/simple faiss-gpu
入门使用：
以下内容转自：
2. Faiss简单上手
首先，Faiss检索相似向量TopK的工程基本都能分为三步：
- 得到向量库；
- 用faiss 构建index，并将向量添加到index中；
- 用faiss index 检索。
好吧......这貌似和废话没啥区别，参考把大象装冰箱需要几个步骤。本段代码摘自Faiss官方文档，很清晰，基本所有的index构建流程都遵循这个步骤。
- 第一步，得到向量：
import numpy as np
d = 64 # 向量维度
nb = 100000 # index向量库的数据量
nq = 10000 # 待检索query的数目
np.random.seed(1234)
xb = np.random.random((nb, d)).astype('float32')
xb[:, 0] += np.arange(nb) / 1000. # index向量库的向量
xq = np.random.random((nq, d)).astype('float32')
xq[:, 0] += np.arange(nq) / 1000. # 待检索的query向量- 第二步，构建索引，这里我们选用暴力检索的方法FlatL2，L2代表构建的index采用的相似度度量方法为L2范数，即欧氏距离：
import faiss
index = faiss.IndexFlatL2(d)
print(index.is_trained) # 输出为True，代表该类index不需要训练，只需要add向量进去即可
index.add(xb) # 将向量库中的向量加入到index中
print(index.ntotal) # 输出index中包含的向量总数，为100000 - 第三步，检索TopK相似query：
k = 4 # topK的K值
D, I = index.search(xq, k)# xq为待检索向量，返回的I为每个待检索query最相似TopK的索引list，D为其对应的距离
print(I[:5])
print(D[-5:])- 打印输出为：
>>>
[[ 0 393 363 78]
[ 1 555 277 364]
[ 2 304 101 13]
[ 3 173 18 182]
[ 4 288 370 531]]
[[ 0. 7.17517328 7.2076292 7.25116253]
[ 0. 6.32356453 6.6845808 6.79994535]
[ 0. 5.79640865 6.39173603 7.28151226]
[ 0. 7.27790546 7.52798653 7.66284657]
[ 0. 6.76380348 7.29512024 7.36881447]]使用：
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")