CLIP-ViT-B-32-256x256-DataComp-s34B-b86K

#!/bin/bash -x
#SBATCH --nodes=24
#SBATCH --gres=gpu:4
#SBATCH --ntasks-per-node=4
#SBATCH --cpus-per-task=12
#SBATCH --time=24:00:00
source /path/miniconda/bin/activate
export CUDA_VISIBLE_DEVICES=0,1,2,3
export MASTER_PORT=12802
master_addr=$(scontrol show hostnames "$SLURM_JOB_NODELIST" | head -n 1)
export MASTER_ADDR=$master_addr"i"
echo "MASTER_ADDR="$MASTER_ADDR
srun --cpu-bind=v --cpus-per-task=12 python -u -m training.main --aug-cfg scale='(0.4, 1.0)' color_jitter='(0.32, 0.32, 0.32, 0.08)' color_jitter_prob=0.8 gray_scale_prob=0.2 use_timm=True \
--save-frequency 1 \
--zeroshot-frequency 1 \
--dataset-type webdataset \
--train-data '/path/to/data' \
--report-to tensorboard \
--train-num-samples 1398270000 \
--warmup 2000 \
--batch-size 896 \
--epochs 24 \
--workers 8 \
--model ViT-B-32-256 \
--logs logs \
--seed 0 \
--ddp-static-graph \
--local-loss \
--gather-with-grad \
--lr 0.001 \
--log-every-n-steps 20 \
--save-most-recent \
--resume latest \
--grad-checkpointing \
--precision amp_bfloat16 \
--beta1 0.9 \
--beta2 0.95 \
--wd 0.2

import torch
from PIL import Image
import open_clip

model, _, preprocess = open_clip.create_model_and_transforms('hf-hub:laion/CLIP-ViT-B-32-256x256-DataComp-s34B-b86K')
model.eval()  # model in train mode by default, impacts some models with BatchNorm or stochastic depth active
tokenizer = open_clip.get_tokenizer('hf-hub:laion/CLIP-ViT-B-32-256x256-DataComp-s34B-b86K')

image = preprocess(Image.open("docs/CLIP.png")).unsqueeze(0)
text = tokenizer(["a diagram", "a dog", "a cat"])

with torch.no_grad(), torch.autocast("cuda"):
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)
    image_features /= image_features.norm(dim=-1, keepdim=True)
    text_features /= text_features.norm(dim=-1, keepdim=True)

    text_probs = (100.0 * image_features @ text_features.T).softmax(dim=-1)

print("Label probs:", text_probs)  # prints: [[1., 0., 0.]]

@article{datacomp,
  title={DataComp: In search of the next generation of multimodal datasets},
  author={Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Orgad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan Bitton, Kalyani Marathe, Stephen Mussmann, Richard Vencu, Mehdi Cherti, Ranjay Krishna, Pang Wei Koh, Olga Saukh, Alexander Ratner, Shuran Song, Hannaneh Hajishirzi, Ali Farhadi, Romain Beaumont, Sewoong Oh, Alex Dimakis, Jenia Jitsev, Yair Carmon, Vaishaal Shankar, Ludwig Schmidt},
  journal={arXiv preprint arXiv:2304.14108},
  year={2023}
}

@inproceedings{Radford2021LearningTV,
  title={Learning Transferable Visual Models From Natural Language Supervision},
  author={Alec Radford and Jong Wook Kim and Chris Hallacy and A. Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever},
  booktitle={ICML},
  year={2021}
}

@software{ilharco_gabriel_2021_5143773,
  author       = {Ilharco, Gabriel and
                  Wortsman, Mitchell and
                  Wightman, Ross and
                  Gordon, Cade and
                  Carlini, Nicholas and
                  Taori, Rohan and
                  Dave, Achal and
                  Shankar, Vaishaal and
                  Namkoong, Hongseok and
                  Miller, John and
                  Hajishirzi, Hannaneh and
                  Farhadi, Ali and
                  Schmidt, Ludwig},
  title        = {OpenCLIP},
  month        = jul,
  year         = 2021,
  note         = {If you use this software, please cite it as below.},
  publisher    = {Zenodo},
  version      = {0.1},
  doi          = {10.5281/zenodo.5143773},
  url          = {https://doi.org/10.5281/zenodo.5143773}
}

@software{cherti_2025_15403103,
  author       = {Cherti, Mehdi and
                  Beaumont, Romain},
  title        = {CLIP benchmark},
  month        = may,
  year         = 2025,
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.15403103},
  url          = {https://doi.org/10.5281/zenodo.15403103},
  swhid        = {swh:1:dir:8cf49a5dd06f59224844a1e767337a1d14ee56c2
                   ;origin=https://doi.org/10.5281/zenodo.15403102;vi
                   sit=swh:1:snp:dd153b26f702d614346bf814f723d59fef3d
                   77a2;anchor=swh:1:rel:cff2aeb98f42583b44fdab5374e9
                   fa71793f2cff;path=CLIP\\_benchmark-main
                  },
}