import cv2
import torch
import torchvision.transforms as T
import numpy as np
from PIL import Image
from sklearn.decomposition import PCA
patch_h = 50
patch_w = 50
feat_dim = 1536 # vitg14
transform = T.Compose([T.GaussianBlur(9, sigma=(0.1, 2.0)), T.Resize((patch_h * 14, patch_w * 14)), T.CenterCrop((patch_h * 14, patch_w * 14)), T.ToTensor(),
T.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)), ])
# model = models.resnet50()
# 加载权重
# model.load_state_dict(torch.load(r'C:\Users\Administrator\.cache\torch\hub\checkpoints\dinov2_vitg14_pretrain.pth'))
dinov2_vitb14 = torch.hub.load('', 'dinov2_vitg14', source='local').cuda()
# print(dinov2_vitb14)
# extract features
features = torch.zeros(4, patch_h * patch_w, feat_dim)
imgs_tensor = torch.zeros(4, 3, patch_h * 14, patch_w * 14).cuda()
img_path = f'./dog.jpeg' # 修改图片路径
i
dinov2 使用实例
猜你喜欢
转载自blog.csdn.net/jacke121/article/details/135021016
今日推荐
周排行