Zero-Shot Object Detection
ZeroModels
Keras
PyTorch
JAX
TensorFlow
owlv2
open-vocabulary
object-detection
Instructions to use zeromodels/owlv2-large-patch14 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/owlv2-large-patch14 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/owlv2-large-patch14") - Keras
How to use zeromodels/owlv2-large-patch14 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/owlv2-large-patch14") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from zeromodels/owlv2-large-patch14: direct link, hf CLI and curl.
- Browser
- Download file 1.75 GB
-
https://huggingface.co/zeromodels/owlv2-large-patch14/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/owlv2-large-patch14/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/owlv2-large-patch14/resolve/main/model.weights.h5
1.75 GB
- Xet hash:
- db3c729c7aeff596c90711ecf1cb55fe5664942bf02aecfd3b7455b7c79d1111
- Size of remote file:
- 1.75 GB
- SHA256:
- e831de67e015f6d2a2595a4a1e0a56f8b3ed883ce78c3b43a545e26996afd4b8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.