导入相关库
import collections
import math
import os
import shutil
import pandas as pd
import torch
import torchvision
from torch import nn
from d2l import torch as d2l下载数据集
d2l.DATA_HUB[cifar10_tiny] (d2l.DATA_URL kaggle_cifar10_tiny.zip,2068874e4…
Li J, Li D, Savarese S, et al. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models[J]. arXiv preprint arXiv:2301.12597, 2023. BLIP-2,是 BLIP 系列的第二篇,同样出自 Salesforce 公司&…