- Depth can be estimated in meters from images of various indoor and outdoor scenes.
how to use
Insall
Depending on the version of timm and torch, a runtime error may occur, so use the following.
pip install timm==0.6.7
pip install torch==2.0.1
git clone https://github.com/isl-org/ZoeDepth.git
cd ZoeDepth
Operation check
python sanity.py
model road
import torch
from zoedepth.utils.misc import get_image_from_url, colorize
zoe = torch.hub.load(".", "ZoeD_N", source="local", pretrained=True)
zoe = zoe.to('cuda')
execution
import cv2
from PIL import Image
img = Image.open("image.jpg")
depth = zoe.infer_pil(img)
colored_depth = colorize(depth)
cv2.imwrite('zoe_depth.png',colored_depth)
🐣
I’m a freelance engineer.
Work consultation
Please feel free to contact us with a brief development description.
rockyshikoku@gmail.com
I am creating applications using machine learning and AR technology.
I send machine learning / AR related information.