Zero-Shot Image Classification
OpenCLIP
clip
vision-language-model
image-text-retrieval
research
long-tail
datacomp
Instructions to use MingliangLiang3/DynamiCS-ViT-B-16-DataComp-DFN with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- OpenCLIP
How to use MingliangLiang3/DynamiCS-ViT-B-16-DataComp-DFN with OpenCLIP:
import open_clip model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms('hf-hub:MingliangLiang3/DynamiCS-ViT-B-16-DataComp-DFN') tokenizer = open_clip.get_tokenizer('hf-hub:MingliangLiang3/DynamiCS-ViT-B-16-DataComp-DFN') - Notebooks
- Google Colab
- Kaggle
Mingliang Liang
Rename DataComp_dinov2_sampling_50k_merger_0.70_probabilities_alpha_0.2_t_0.5_sha256.json to datacomp_dfn_sampling_probs_sha256.json
e1dc181 verified - Xet hash:
- 3ec138e0b91a6a16a9130fbf708a6a5f8bb0f75d091f37ee45fe1f72bde82d56
- Size of remote file:
- 10.4 GB
- SHA256:
- 8f353ff03ac31d0816575195b108821da42bbd3c1aa9eca95c2fd9b1afde2c9c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.