Image Feature Extraction
timm
Safetensors
sapiens
sapiens2
Transformers
vision-transformer
human-centric
pretrained-backbone
feature-extraction
Instructions to use timm/vit_large_patch16_sapiens2.fb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- timm
How to use timm/vit_large_patch16_sapiens2.fb with timm:
import timm model = timm.create_model("hf-hub:timm/vit_large_patch16_sapiens2.fb", pretrained=True) - sapiens
How to use timm/vit_large_patch16_sapiens2.fb with sapiens:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- sapiens2
How to use timm/vit_large_patch16_sapiens2.fb with sapiens2:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Transformers
How to use timm/vit_large_patch16_sapiens2.fb with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="timm/vit_large_patch16_sapiens2.fb")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("timm/vit_large_patch16_sapiens2.fb", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from timm/vit_large_patch16_sapiens2.fb: direct link, hf CLI and curl.
- Browser
- Download file 784 Bytes
-
https://huggingface.co/timm/vit_large_patch16_sapiens2.fb/resolve/f2cb24908418113aec545b966ce4cc96a1cfd9dc/config.json
- Command line
-
hf download hf://timm/vit_large_patch16_sapiens2.fb@f2cb24908418113aec545b966ce4cc96a1cfd9dc/config.json
-
curl -L -o config.json https://huggingface.co/timm/vit_large_patch16_sapiens2.fb/resolve/f2cb24908418113aec545b966ce4cc96a1cfd9dc/config.json
784 Bytes
| { | |
| "architecture": "vit_large_patch16_sapiens2", | |
| "num_classes": 0, | |
| "num_features": 1024, | |
| "global_pool": "token", | |
| "pretrained_cfg": { | |
| "tag": "fb", | |
| "custom_load": false, | |
| "input_size": [ | |
| 3, | |
| 1024, | |
| 768 | |
| ], | |
| "min_input_size": [ | |
| 3, | |
| 256, | |
| 192 | |
| ], | |
| "fixed_input_size": false, | |
| "interpolation": "bilinear", | |
| "crop_pct": 1.0, | |
| "crop_mode": "squash", | |
| "mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "num_classes": 0, | |
| "pool_size": null, | |
| "first_conv": "patch_embed.proj", | |
| "classifier": "head", | |
| "license": "sapiens2-license", | |
| "origin_url": "https://github.com/facebookresearch/sapiens2", | |
| "paper_ids": "arXiv:2604.21681" | |
| } | |
| } |