Instructions to use zeromodels/depth_anything_v2_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use zeromodels/depth_anything_v2_small 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_v2_small") - DepthAnythingV2
How to use zeromodels/depth_anything_v2_small with DepthAnythingV2:
# Install from https://github.com/DepthAnything/Depth-Anything-V2 # Load the model and infer depth from an image import cv2 import torch from depth_anything_v2.dpt import DepthAnythingV2 # instantiate the model model = DepthAnythingV2(encoder="<ENCODER>", features=<NUMBER_OF_FEATURES>, out_channels=<OUT_CHANNELS>) # load the weights filepath = hf_hub_download(repo_id="zeromodels/depth_anything_v2_small", filename="depth_anything_v2_<ENCODER>.pth", repo_type="model") state_dict = torch.load(filepath, map_location="cpu") model.load_state_dict(state_dict).eval() raw_img = cv2.imread("your/image/path") depth = model.infer_image(raw_img) # HxW raw depth map in numpy - Notebooks
- Google Colab
- Kaggle
Migrate to zeromodels (rename kf_*.json -> zm_*.json, fix refs in config + README, ensure tag + badge)
62b7993 verified | { | |
| "library_name": "zeromodels", | |
| "zeromodels_version": "1.2.1", | |
| "model_module": "zeromodels.models.depth_anything_v2", | |
| "model_class": "DepthAnythingV2DepthEstimation", | |
| "variant": "depth_anything_v2_small", | |
| "weights": "model.weights.h5", | |
| "schema_version": 2, | |
| "weight_dtype": "float32", | |
| "model_type": "depth_anything", | |
| "vision_config": { | |
| "backbone_dim": 384, | |
| "backbone_depth": 12, | |
| "backbone_num_heads": 6, | |
| "out_indices": [ | |
| 3, | |
| 6, | |
| 9, | |
| 12 | |
| ], | |
| "neck_hidden_sizes": [ | |
| 48, | |
| 96, | |
| 192, | |
| 384 | |
| ], | |
| "fusion_hidden_size": 64, | |
| "reassemble_factors": [ | |
| 4, | |
| 2, | |
| 1, | |
| 0.5 | |
| ], | |
| "depth_estimation_type": "relative", | |
| "max_depth": 1.0, | |
| "image_size": 518 | |
| } | |
| } |