模型:
Salesforce/blip-itm-large-coco
预印本库:
arxiv:2201.12086许可:
bsd-3-clauseBLIP在COCO数据集上使用大型架构(使用ViT大型骨干)进行图像-文本匹配训练的模型卡片。
Pull figure from BLIP official repo |
来自 paper 的作者在摘要中写道:
视觉-语言预训练(VLP)在许多视觉-语言任务的性能上取得了进展。然而,大多数现有的预训练模型只擅长理解型任务或生成型任务。此外,通过扩大使用从网络收集的带有噪声的图像-文本对数据集来提高性能,这是一种次优的监督来源。在本文中,我们提出了BLIP,一种新的VLP框架,可以灵活地用于视觉-语言理解和生成任务。BLIP通过引导标题有效利用噪声网络数据,其中一个标题生成器生成合成标题,一个过滤器去除噪声标题。我们在广泛的视觉-语言任务中取得了最先进的结果,如图像-文本检索(平均召回率@1提高2.7%)、图像描述(CIDEr提高2.8%)和VQA(VQA分数提高1.6%)。BLIP还展示了强大的泛化能力,可以直接以零样本的方式转移到视频-语言任务上。发布了代码、模型和数据集。
您可以将此模型用于有条件和无条件的图像描述。
import requests from PIL import Image from transformers import BlipProcessor, BlipForImageTextRetrieval processor = BlipProcessor.from_pretrained("Salesforce/blip-itm-large-coco") model = BlipForImageTextRetrieval.from_pretrained("Salesforce/blip-itm-large-coco") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "A woman and a dog sitting together in a beach." inputs = processor(raw_image, question, return_tensors="pt") itm_scores = model(**inputs)[0] cosine_score = model(**inputs, use_itm_head=False)[0]在GPU上运行模型 完整精度 点击展开
import requests from PIL import Image from transformers import BlipProcessor, BlipForImageTextRetrieval processor = BlipProcessor.from_pretrained("Salesforce/blip-itm-large-coco") model = BlipForImageTextRetrieval.from_pretrained("Salesforce/blip-itm-large-coco").to("cuda") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "A woman and a dog sitting together in a beach." inputs = processor(raw_image, question, return_tensors="pt").to("cuda") itm_scores = model(**inputs)[0] cosine_score = model(**inputs, use_itm_head=False)[0]半精度(float16) 点击展开
import torch import requests from PIL import Image from transformers import BlipProcessor, BlipForImageTextRetrieval processor = BlipProcessor.from_pretrained("Salesforce/blip-itm-large-coco") model = BlipForImageTextRetrieval.from_pretrained("Salesforce/blip-itm-large-coco", torch_dtype=torch.float16).to("cuda") img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB') question = "A woman and a dog sitting together in a beach." inputs = processor(raw_image, question, return_tensors="pt").to("cuda", torch.float16) itm_scores = model(**inputs)[0] cosine_score = model(**inputs, use_itm_head=False)[0]
@misc{https://doi.org/10.48550/arxiv.2201.12086, doi = {10.48550/ARXIV.2201.12086}, url = {https://arxiv.org/abs/2201.12086}, author = {Li, Junnan and Li, Dongxu and Xiong, Caiming and Hoi, Steven}, keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences}, title = {BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation}, publisher = {arXiv}, year = {2022}, copyright = {Creative Commons Attribution 4.0 International} }