salesforce/BLIP: PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation - BLIP

salesforce/BLIP

Fork 0

mirror of https://github.com/salesforce/BLIP.git synced 2026-02-27 14:33:56 +00:00

Go to file

root f5eacc9f08 add datasets

2022-01-27 12:51:05 +00:00

configs

init

2022-01-27 12:37:45 +00:00

data

add datasets

2022-01-27 12:51:05 +00:00

models

Delete models/__pycache__ directory

2022-01-27 20:38:44 +08:00

transform

Delete transform/__pycache__ directory

2022-01-27 20:38:55 +08:00

demo.ipynb

init

2022-01-27 12:37:45 +00:00

eval_nocaps.py

init

2022-01-27 12:37:45 +00:00

pretrain.py

init

2022-01-27 12:37:45 +00:00

README.md

Update README.md

2022-01-27 20:49:49 +08:00

requirements.txt

init

2022-01-27 12:37:45 +00:00

train_caption.py

init

2022-01-27 12:37:45 +00:00

train_nlvr.py

init

2022-01-27 12:37:45 +00:00

train_retrieval.py

init

2022-01-27 12:37:45 +00:00

train_vqa.py

init

2022-01-27 12:37:45 +00:00

utils.py

init

2022-01-27 12:37:45 +00:00

README.md

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

This is the PyTorch implementation of the BLIP paper.

Catalog:

Inference demo
Pre-trained and finetuned checkpoints
Pre-training code
Finetuning code for Image-Text Retrieval, Image Captioning, VQA, and NLVR2
Download of bootstrapped image-text dataset

Inference demo (Image Captioning and VQA):

Run our interactive demo using Colab notebook (no GPU needed):

Description

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

image-captioning image-text-retrieval vision-and-language-pre-training vision-language vision-language-transformer visual-question-answering visual-reasoning

Readme 9.7 MiB