Hi folks!
ZoeDepth is now available in the Transformers library, enabling easy inference in a few lines of code.
Here's how to use it:
from transformers import pipeline
from PIL import Image
import requests
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)
pipe = pipeline(task="depth-estimation", model="Intel/zoedepth-nyu-kitti")
result = pipe(image)
depth = result["depth"]
You can also do the pre- and postprocessing yourself as explained here.
Hi folks!
ZoeDepth is now available in the Transformers library, enabling easy inference in a few lines of code.
Here's how to use it:
You can also do the pre- and postprocessing yourself as explained here.