Instructions to use keras/sam_base_sa1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/sam_base_sa1b with KerasHub:
import keras_hub # Create a ImageSegmenter model task = keras_hub.models.ImageSegmenter.from_preset("hf://keras/sam_base_sa1b")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/sam_base_sa1b") - Keras
How to use keras/sam_base_sa1b with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://keras/sam_base_sa1b") - Notebooks
- Google Colab
- Kaggle
| { | |
| "module": "keras_hub.src.models.sam.sam_image_segmenter_preprocessor", | |
| "class_name": "SAMImageSegmenterPreprocessor", | |
| "config": { | |
| "name": "sam_image_segmenter_preprocessor", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "image_converter": { | |
| "module": "keras_hub.src.models.sam.sam_image_converter", | |
| "class_name": "SAMImageConverter", | |
| "config": { | |
| "name": "sam_image_converter", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "image_size": [ | |
| 1024, | |
| 1024 | |
| ], | |
| "scale": 0.00392156862745098, | |
| "offset": null, | |
| "interpolation": "bilinear", | |
| "crop_to_aspect_ratio": true | |
| }, | |
| "registered_name": "keras_hub>SAMImageConverter" | |
| }, | |
| "config_file": "preprocessor.json" | |
| }, | |
| "registered_name": "keras_hub>SAMImageSegmenterPreprocessor" | |
| } |