Instructions to use zeromodels/grounding_dino_tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/grounding_dino_tiny with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/grounding_dino_tiny") - Keras
How to use zeromodels/grounding_dino_tiny with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/grounding_dino_tiny") - Notebooks
- Google Colab
- Kaggle
Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)
1b447be verified Download zm_preprocessor.json from zeromodels/grounding_dino_tiny: direct link, hf CLI and curl.
- Browser
- Download file 479 Bytes
-
https://huggingface.co/zeromodels/grounding_dino_tiny/resolve/main/zm_preprocessor.json
- Command line
-
hf download hf://zeromodels/grounding_dino_tiny/zm_preprocessor.json
-
curl -L -o zm_preprocessor.json https://huggingface.co/zeromodels/grounding_dino_tiny/resolve/main/zm_preprocessor.json
479 Bytes
| { | |
| "library_name": "zeromodels", | |
| "zeromodels_version": "1.1.3", | |
| "preprocessor_module": "zeromodels.models.grounding_dino", | |
| "preprocessor_class": "GroundingDinoImageProcessor", | |
| "variant": "grounding_dino_tiny", | |
| "shortest_edge": 800, | |
| "longest_edge": 1333, | |
| "image_mean": [ | |
| 0.48500001430511475, | |
| 0.4560000002384186, | |
| 0.4059999883174896 | |
| ], | |
| "image_std": [ | |
| 0.2290000021457672, | |
| 0.2240000069141388, | |
| 0.22499999403953552 | |
| ], | |
| "data_format": null | |
| } |