salesforce/BLIP
1
0
Fork 0
mirror of https://github.com/salesforce/BLIP.git synced 2026-04-30 12:21:12 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Junnan Li
2022-01-27 21:40:36 +08:00
committed by GitHub
parent 08627003f8
commit 0f8d19bbc9
1 changed files with 11 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
README.md
View File

@@ -1,5 +1,7 @@
## BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation ## BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation
<img src="img.png" width="600">
This is the PyTorch implementation of the <a href="https://arxiv.org/abs/2107.07651">BLIP paper</a>. The code has been tested on PyTorch 1.9 and 1.10. This is the PyTorch implementation of the <a href="https://arxiv.org/abs/2107.07651">BLIP paper</a>. The code has been tested on PyTorch 1.9 and 1.10.
To install the dependencies, run <pre/>pip install -r requirements.txt</pre> To install the dependencies, run <pre/>pip install -r requirements.txt</pre>
@@ -65,3 +67,12 @@ NLVR2 | <a href="https://storage.googleapis.com/sfr-vision-language-research/BLI
3. To finetune the pre-trained checkpoint using 16 A100 GPUs, first set 'pretrained' in configs/nlvr.yaml as "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base.pth". Then run: 3. To finetune the pre-trained checkpoint using 16 A100 GPUs, first set 'pretrained' in configs/nlvr.yaml as "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base.pth". Then run:
<pre>python -m torch.distributed.run --nproc_per_node=16 --use_env train_nlvr.py </pre> <pre>python -m torch.distributed.run --nproc_per_node=16 --use_env train_nlvr.py </pre>
### Citation
If you find this code to be useful for your research, please consider citing.
<pre>
@inproceedings{ALBEF,
title={Align before Fuse: Vision and Language Representation Learning with Momentum Distillation},
author={Junnan Li and Ramprasaath R. Selvaraju and Akhilesh Deepak Gotmare and Shafiq Joty and Caiming Xiong and Steven Hoi},
year={2021},
booktitle={NeurIPS},
}</pre>