Image Segmentation
ZeroModels
Keras
PyTorch
JAX
TensorFlow
mobilevit
deeplabv3
semantic-segmentation
Instructions to use zeromodels/mobilevit_s_deeplabv3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/mobilevit_s_deeplabv3 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/mobilevit_s_deeplabv3") - Keras
How to use zeromodels/mobilevit_s_deeplabv3 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/mobilevit_s_deeplabv3") - Notebooks
- Google Colab
- Kaggle
Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)
df3c962 verified Download zm_preprocessor.json from zeromodels/mobilevit_s_deeplabv3: direct link, hf CLI and curl.
- Browser
- Download file 477 Bytes
-
https://huggingface.co/zeromodels/mobilevit_s_deeplabv3/resolve/main/zm_preprocessor.json
- Command line
-
hf download hf://zeromodels/mobilevit_s_deeplabv3/zm_preprocessor.json
-
curl -L -o zm_preprocessor.json https://huggingface.co/zeromodels/mobilevit_s_deeplabv3/resolve/main/zm_preprocessor.json
477 Bytes
| { | |
| "library_name": "zeromodels", | |
| "preprocessor_module": "zeromodels.models.mobilevit", | |
| "preprocessor_class": "MobileViTImageProcessor", | |
| "variant": null, | |
| "size": { | |
| "shortest_edge": 544 | |
| }, | |
| "crop_size": { | |
| "height": 512, | |
| "width": 512 | |
| }, | |
| "resample": "bilinear", | |
| "do_resize": true, | |
| "do_center_crop": true, | |
| "do_rescale": true, | |
| "rescale_factor": 0.00392156862745098, | |
| "do_flip_channel_order": true, | |
| "return_tensor": true, | |
| "data_format": null | |
| } |