Instructions to use depth-anything/Depth-Anything-V2-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- DepthAnythingV2
How to use depth-anything/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="vits", features=64, out_channels=[48, 96, 192, 384]) # load the weights filepath = hf_hub_download(repo_id="depth-anything/Depth-Anything-V2-Small", filename="depth_anything_v2_vits.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
SafeTensors version
Browse filesThis is a safetensors version of the torch weights file. I first created it in my own space [0], until I realized I should better put it here. These are my first steps contributing on HF so please let me know if anything is out of order :)
[0] https://huggingface.co/jeroenvlek/depth-anything-v2-safetensors
depth_anything_v2_vits.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07635472183d063a80e6b2d78645ab944a9210fd973b1c88e4b7e3ba23981f75
|
| 3 |
+
size 99165428
|