Instructions to use zeromodels/mask2former-swin-tiny-coco-instance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/mask2former-swin-tiny-coco-instance 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/mask2former-swin-tiny-coco-instance") - Keras
How to use zeromodels/mask2former-swin-tiny-coco-instance 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/mask2former-swin-tiny-coco-instance") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from zeromodels/mask2former-swin-tiny-coco-instance: direct link, hf CLI and curl.
- Browser
- Download file 191 MB
-
https://huggingface.co/zeromodels/mask2former-swin-tiny-coco-instance/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/mask2former-swin-tiny-coco-instance/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/mask2former-swin-tiny-coco-instance/resolve/main/model.weights.h5
191 MB
- Xet hash:
- 753f7b6a8aa3838bd9c290cb36dd08421dd2cb43e4e0ac0b928946138e6f0036
- Size of remote file:
- 191 MB
- SHA256:
- ba55c71693eb7c93a3920b9e1753b3afa85b00b817f5457d6779971cc12a80df
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.