CV / Depth-Anything

Depth-Anything-ViTS

Depth-Anything V1 (ViT-S backbone) outputs a 224x224 relative depth map. Same I/O as V2 but slightly more accurate (AbsRel 0.13 vs 0.147). INFERNO colormap visualization, depth statistics API.

1 Downloads

Größe

32 MB

Speicher

4GB+

Präzision

Hailo HEF / HailoRT 4.23.x

Wähle das Gerät, das du verwendest. Die Einrichtungsanleitung und Dokumentation werden entsprechend aktualisiert.

Plattform

Inferenz-Engine

Erste Schritte

Bereitstellen

sudo docker run --rm \
  --name cm5-hailo8-depth-anything-vits \
  --privileged \
  --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.4.23.0:/usr/lib/libhailort.so.4.23.0:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo8-cv/depth_anything_vits:latest \
  python web_detection.py --model_path model/depth_anything_vits.hef --video_path video/test.mp4

REST API

Verwende die REST API für die Inferenz. Kopiere die folgenden Befehle.

Curl

curl -X POST "http://<Board_IP>:8000/api/models/depth_anything_vits/predict" \
  -F "file=@test.jpg"

Python

import requests
response = requests.post(
    "http://<Board_IP>:8000/api/models/depth_anything_vits/predict",
    files={"file": open("test.jpg", "rb")},
    timeout=30,
)
print(response.json())

Modelldetails

Depth-Anything-ViTS on reComputer R Series (CM5 + Hailo-8)

Depth-Anything V1 (ViT-S backbone) performs zero-shot monocular depth estimation on Hailo-8. Same I/O as V2 but slightly more accurate (AbsRel 0.13 vs 0.147). INFERNO colormap visualization, depth statistics API.

Model Info

Property	Value
Architecture	ViT-S (Depth-Anything V1)
Task	Zero-shot depth estimation
Input	224x224x3 RGB
Output	Depth map 224x224x1 (relative)
Parameters	24.2M
AbsRel	0.13
HEF	Hailo Model Zoo v2.19.0, Hailo-8

Run With Demo Video

bash

sudo docker run --rm \
  --name cm5-hailo8-depth-anything-vits \
  --privileged \
  --net=host \
  -e PYTHONUNBUFFERED=1 \
  --device /dev/hailo0:/dev/hailo0 \
  -v /usr/lib/libhailort.so.4.23.0:/usr/lib/libhailort.so.4.23.0:ro \
  -v /usr/lib/libhailort.so:/usr/lib/libhailort.so:ro \
  ghcr.io/seeed-projects/recomputer-hailo8-cv/depth_anything_vits:latest \
  python web_detection.py --model_path model/depth_anything_vits.hef --video_path video/test.mp4

REST API

bash

curl -X POST "http://<Board_IP>:8000/api/models/depth_anything_vits/predict" \
  -F "file=@test.jpg"

Returns depth_stats (min, max, mean, std).

Endpoint	Method	Purpose
`/api/models/depth_anything_vits/predict`	POST	Depth statistics (JSON)
`/api/video_feed`	GET	MJPEG with INFERNO depth overlay

Development Notes

Source: src/rpi5_hailo8_depth_anything_vits/
Container: ghcr.io/seeed-projects/recomputer-hailo8-cv/depth_anything_vits:latest
Family: depth_anything (variants v2_vits / vits)

Eingaben und Ausgaben

Input: image, video, or USB camera frame. Output: relative depth map with INFERNO colormap overlay on MJPEG preview, plus depth statistics (min/max/mean/std) via API.