Instructions to use zeromodels/depth_anything_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeromodels/depth_anything_base with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://zeromodels/depth_anything_base") - Notebooks
- Google Colab
- Kaggle
Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)
5d185b7 verified | { | |
| "library_name": "zeromodels", | |
| "zeromodels_version": "1.2.1", | |
| "model_module": "zeromodels.models.depth_anything_v1", | |
| "model_class": "DepthAnythingV1DepthEstimation", | |
| "variant": "depth_anything_base", | |
| "weights": "model.weights.h5", | |
| "schema_version": 2, | |
| "weight_dtype": "float32", | |
| "model_type": "depth_anything", | |
| "vision_config": { | |
| "backbone_dim": 768, | |
| "backbone_depth": 12, | |
| "backbone_num_heads": 12, | |
| "out_indices": [ | |
| 9, | |
| 10, | |
| 11, | |
| 12 | |
| ], | |
| "neck_hidden_sizes": [ | |
| 96, | |
| 192, | |
| 384, | |
| 768 | |
| ], | |
| "fusion_hidden_size": 128, | |
| "reassemble_factors": [ | |
| 4, | |
| 2, | |
| 1, | |
| 0.5 | |
| ], | |
| "depth_estimation_type": "relative", | |
| "max_depth": 1.0, | |
| "image_size": 518 | |
| } | |
| } |