BLIP Math

🚀 BLIP - Math

This model is fine - tuned on a mathematical multi - modal dataset. It has two output heads: text generation and scoring. We offer the weight file 'pytorch_model.bin' for the text - generation part of the model.

You'll need 4 input sources, including two text inputs and two image inputs: 'problem_body', 'student_response', 'question_image', and 'student_image'.

To perform conditional text generation:

• Concatenate the text as follows: text = 'problem:' + ' ' + [problem_body] + ' ' + 'student:' + [student_response] + ' ' + 'response:'

• Concatenate [question_image] and [student_image] vertically, keeping [question_image] on top and choosing the larger of the two image sizes.

For all other uses, follow the same procedures as with the BLIP model.

If you have further questions or need help with specific code or implementation details, feel free to ask.

🚀 Quick Start

BLIP: Bootstrapping Language - Image Pre - training for Unified Vision - Language Understanding and Generation

This is a model card for image captioning, pretrained on the COCO dataset with a base architecture (using a ViT base backbone).

TL;DR

The authors of the paper write in the abstract:

Vision - Language Pre - training (VLP) has advanced the performance for many vision - language tasks. However, most existing pre - trained models only excel in either understanding - based tasks or generation - based tasks. Furthermore, performance improvement has been largely achieved by scaling up the dataset with noisy image - text pairs collected from the web, which is a suboptimal source of supervision. In this paper, we propose BLIP, a new VLP framework which transfers flexibly to both vision - language understanding and generation tasks. BLIP effectively utilizes the noisy web data by bootstrapping the captions, where a captioner generates synthetic captions and a filter removes the noisy ones. We achieve state - of - the - art results on a wide range of vision - language tasks, such as image - text retrieval (+2.7% in average recall@1), image captioning (+2.8% in CIDEr), and VQA (+1.6% in VQA score). BLIP also demonstrates strong generalization ability when directly transferred to video - language tasks in a zero - shot manner. Code, models, and datasets are released.

✨ Features

You can use this model for conditional and un - conditional image captioning

💻 Usage Examples

Using the Pytorch model

Running the model on CPU

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")

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')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog

Running the model on GPU

In full precision

import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").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')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda")

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog

In half precision (float16)

import torch
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration

processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", 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')

# conditional image captioning
text = "a photography of"
inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
# >>> a photography of a woman and her dog

# unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)

out = model.generate(**inputs)
print(processor.decode(out[0], skip_special_tokens=True))
>>> a woman sitting on the beach with her dog

📚 Documentation

BibTex and citation info

@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}
}

📄 License

This project is licensed under the bsd - 3 - clause license.