Instructions to use depth-anything/Depth-Anything-V2-Small-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use depth-anything/Depth-Anything-V2-Small-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("depth-estimation", model="depth-anything/Depth-Anything-V2-Small-hf")# Load model directly from transformers import AutoImageProcessor, AutoModelForDepthEstimation processor = AutoImageProcessor.from_pretrained("depth-anything/Depth-Anything-V2-Small-hf") model = AutoModelForDepthEstimation.from_pretrained("depth-anything/Depth-Anything-V2-Small-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Android + OpenCL implementation β monocular depth on-device on non-flagship phones (Adreno 6xx)
#3
by a8nova - opened
Hi! I wanted to share an Android + OpenCL implementation of Depth-Anything-V2-Small, in case anyone wants to run it on a phone:
- Try it: Edgi on Google Play β runs fully on-device, no cloud.
- Open source: the app is built on top of the open-source adreno-llms inference engine β https://github.com/a8nova/adreno-llms β pure C++/OpenCL with hand-written kernels tuned for Adreno.
It's tuned and tested on Adreno 6xx GPUs β the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) β and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it produces a full depth map at 518Γ686 fp16 in ~5.2 s/frame, with cosine 0.99999 vs the PyTorch reference.
Hope it's useful β happy to answer questions!