GLPN 在 KITTI 上的微调

GLPN（全局-局部路径网络）模型在 KITTI 数据集上进行了微调，用于单目深度估计。该模型由 Kim 等人在论文 Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth 中提出，并首次在 this repository 中发布。

免责声明：发布 GLPN 的团队未为此模型编写模型卡片，因此该模型卡片由 Hugging Face 团队编写。

模型描述

GLPN 使用 SegFormer 作为主干，并在其上方添加了一个轻量级的头部用于深度估计。

预期用途与限制

您可以使用原始模型进行单目深度估计。请参阅 model hub 获取您感兴趣的任务的经过微调的版本。

使用方法

以下是使用该模型的方法：

from transformers import GLPNFeatureExtractor, GLPNForDepthEstimation
import torch
import numpy as np
from PIL import Image
import requests

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

feature_extractor = GLPNFeatureExtractor.from_pretrained("vinvino02/glpn-kitti")
model = GLPNForDepthEstimation.from_pretrained("vinvino02/glpn-kitti")

# prepare image for the model
inputs = feature_extractor(images=image, return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)
    predicted_depth = outputs.predicted_depth

# interpolate to original size
prediction = torch.nn.functional.interpolate(
    predicted_depth.unsqueeze(1),
    size=image.size[::-1],
    mode="bicubic",
    align_corners=False,
)

# visualize the prediction
output = prediction.squeeze().cpu().numpy()
formatted = (output * 255 / np.max(output)).astype("uint8")
depth = Image.fromarray(formatted)

有关更多代码示例，请参阅 documentation 。

BibTeX 引用条目和引用信息

@article{DBLP:journals/corr/abs-2201-07436,
  author    = {Doyeon Kim and
               Woonghyun Ga and
               Pyunghwan Ahn and
               Donggyu Joo and
               Sehwan Chun and
               Junmo Kim},
  title     = {Global-Local Path Networks for Monocular Depth Estimation with Vertical
               CutDepth},
  journal   = {CoRR},
  volume    = {abs/2201.07436},
  year      = {2022},
  url       = {https://arxiv.org/abs/2201.07436},
  eprinttype = {arXiv},
  eprint    = {2201.07436},
  timestamp = {Fri, 21 Jan 2022 13:57:15 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2201-07436.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}