Instructions to use keras/dfine_small_coco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/dfine_small_coco with KerasHub:
import keras_hub # Create a ObjectDetector model task = keras_hub.models.ObjectDetector.from_preset("hf://keras/dfine_small_coco")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/dfine_small_coco") - Keras
How to use keras/dfine_small_coco 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/dfine_small_coco") - Notebooks
- Google Colab
- Kaggle
| { | |
| "module": "keras_hub.src.models.d_fine.d_fine_object_detector_preprocessor", | |
| "class_name": "DFineObjectDetectorPreprocessor", | |
| "config": { | |
| "name": "d_fine_object_detector_preprocessor", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "image_converter": { | |
| "module": "keras_hub.src.models.d_fine.d_fine_image_converter", | |
| "class_name": "DFineImageConverter", | |
| "config": { | |
| "name": "d_fine_image_converter", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "float32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "image_size": [ | |
| 640, | |
| 640 | |
| ], | |
| "scale": 0.00392156862745098, | |
| "offset": null, | |
| "interpolation": "bilinear", | |
| "antialias": false, | |
| "crop_to_aspect_ratio": true, | |
| "pad_to_aspect_ratio": false, | |
| "bounding_box_format": "yxyx" | |
| }, | |
| "registered_name": "keras_hub>DFineImageConverter" | |
| }, | |
| "config_file": "preprocessor.json" | |
| }, | |
| "registered_name": "keras_hub>DFineObjectDetectorPreprocessor" | |
| } |