ModelPublicadoExterno

Depth Anything Vits14

The model card for our paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.

Fuentehuggingface.co/LiheYoung/depth_anything_vits14/tree/1bee667edbfec7f9b345abaffec8c9c2bd5293c2

TipoOtherVersiónRevision 1bee667Bcalidad

Fuente del modelo

Tipo: Other
Tamaño del archivo: 94,6 MB
Versión: vRevision 1bee667
Actualizado: 10 oct 2026
Descargas: 3,7 mil
Fuente: Hugging Face

Descripción de la fuente

Depth Anything model, small

The model card for our paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.

You may also try our demo and visit our project page.

Installation

First, install the Depth Anything package:

git clone https://github.com/LiheYoung/Depth-Anything
cd Depth-Anything
pip install -r requirements.txt

Usage

Here's how to run the model:

import numpy as np
from PIL import Image
import cv2
import torch

from depth_anything.dpt import DepthAnything
from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet
from torchvision.transforms import Compose

model = DepthAnything.from_pretrained("LiheYoung/depth_anything_vitl14")

transform = Compose([
        Resize(
            width=518,
            height=518,
            resize_target=False,
            keep_aspect_ratio=True,
            ensure_multiple_of=14,
            resize_method='lower_bound',
            image_interpolation_method=cv2.INTER_CUBIC,
        ),
        NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
        PrepareForNet(),
    ])

image = Image.open("...")
image = np.array(image) / 255.0
image = transform({'image': image})['image']
image = torch.from_numpy(image).unsqueeze(0)

depth = model(image)

Fuentes

1 fuente

Hugging FacePrincipalVersión 1bee667edbfec7f9b345abaffec8c9c2bd5293c2

huggingface.co/LiheYoung/depth_anything_vits14/tree/1bee667edbfec7f9b345abaffec8c9c2bd5293c2

Verificado 25 ago

Artefactos del modelo

1 artefacto

pytorch_model.bin

bin · 94,6 MB · SHA-256 ba0ab5365610…2082 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme25 agohuggingface.co/LiheYoung/depth_anything_vits14

--- tags: - depth_anything - depth-estimation --- # Depth Anything model, small The model card for our paper [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://arxiv.org/abs/2401.10891). You may also try our [demo](https://huggingface.co/spaces/LiheYoung/Depth-Anything) and visit our [project page](https://depth-anything.github.io/). ## Installation First, install the Depth Anything package: ``` git clone https://github.com/LiheYoung/Depth-Anything cd Depth-Anything pip install -r requirements.txt ``` ## Usage Here's how to run the model: ```python import numpy as np from PIL import Image import cv2 import torch from depth_anything.dpt import DepthAnything from depth_anything.util.transform import Resize, NormalizeImage, PrepareForNet from torchvision.transforms import Compose model = DepthAnything.from_pretrained("LiheYoung/depth_anything_vitl14") transform = Compose([ Resize( width=518, height=518, resize_target=False, keep_aspect_ratio=True, ensure_multiple_of=14, resize_method='lower_bound', image_interpolation_method=cv2.INTER_CUBIC, ), NormalizeImage(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), PrepareForNet(), ]) image = Image.open("...") image = np.array(image) / 255.0 image = transform({'image': image})['image'] image = torch.from_numpy(image).unsqueeze(0) depth = model(image) ```

Note25 agohuggingface.co/LiheYoung/depth_anything_vits14

Source context: 3731 downloads · 9 likes · Pipeline depth-estimation · Library transformers · Repo LiheYoung/depth_anything_vits14