Depth Estimation
Transformers
Safetensors
DepthAnythingV2
depth_anything_v2
feature-extraction
custom_code
Instructions to use bigshanedogg/Depth-Anything-V2-Large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigshanedogg/Depth-Anything-V2-Large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="bigshanedogg/Depth-Anything-V2-Large", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bigshanedogg/Depth-Anything-V2-Large", trust_remote_code=True, device_map="auto") - DepthAnythingV2
How to use bigshanedogg/Depth-Anything-V2-Large 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 huggingface_hub import hf_hub_download 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="bigshanedogg/Depth-Anything-V2-Large", filename="depth_anything_v2_<ENCODER>.pth", repo_type="model") state_dict = torch.load(filepath, map_location="cpu") model.load_state_dict(state_dict) model.eval() raw_img = cv2.imread("your/image/path") depth = model.infer_image(raw_img) # HxW raw depth map in numpy - Notebooks
- Google Colab
- Kaggle
Download config.json from bigshanedogg/Depth-Anything-V2-Large: direct link, hf CLI and curl.
- Browser
- Download file 627 Bytes
-
https://huggingface.co/bigshanedogg/Depth-Anything-V2-Large/resolve/main/config.json
- Command line
-
hf download hf://bigshanedogg/Depth-Anything-V2-Large/config.json
-
curl -L -o config.json https://huggingface.co/bigshanedogg/Depth-Anything-V2-Large/resolve/main/config.json
627 Bytes
| { | |
| "architectures": [ | |
| "DepthAnythingV2ForDepthEstimation" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_depth_anything_v2.DepthAnythingV2Config", | |
| "AutoModel": "modeling_depth_anything_v2.DepthAnythingV2ForDepthEstimation", | |
| "AutoModelForDepthEstimation": "modeling_depth_anything_v2.DepthAnythingV2ForDepthEstimation" | |
| }, | |
| "dtype": "float32", | |
| "encoder": "vitl", | |
| "features": 256, | |
| "input_size": 518, | |
| "max_depth": null, | |
| "model_type": "depth_anything_v2", | |
| "out_channels": [ | |
| 256, | |
| 512, | |
| 1024, | |
| 1024 | |
| ], | |
| "transformers_version": "5.20.2", | |
| "use_bn": false, | |
| "use_clstoken": false | |
| } | |