huchenlei/Depth-Anything
1
0
Fork 0
mirror of https://github.com/huchenlei/Depth-Anything.git synced 2026-01-26 15:29:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Lihe Yang
2024-01-25 21:22:16 +08:00
committed by GitHub
parent d4aa13cd2e
commit 801910678a
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
metric_depth/README.md
View File

@@ -38,10 +38,9 @@ Outdoor: KITTI $\rightarrow$ Virtual KITTI 2 and DIODE Outdoor
## Pre-trained models
We provide two pre-trained models ([download](https://huggingface.co/spaces/LiheYoung/Depth-Anything/tree/main/checkpoints_metric_depth)), one for *indoor* metric depth estimation trained on NYUv2, and the other for *outdoor* metric depth estimation trained on KITTI.
## Pre-trained metric depth estimation models
We provide [two pre-trained models](https://huggingface.co/spaces/LiheYoung/Depth-Anything/tree/main/checkpoints_metric_depth), one for *indoor* metric depth estimation trained on NYUv2, and the other for *outdoor* metric depth estimation trained on KITTI.
## Installation
@@ -68,6 +67,8 @@ python evaluate.py -m zoedepth --pretrained_resource="local::./checkpoints/depth
## Training
Please first download our Depth Anything pre-trained models [here](https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth), and put it under the ``checkpoints`` directory.
```bash
python train_mono.py -m zoedepth -d <nyu | kitti> --pretrained_resource=""
```
@@ -85,4 +86,4 @@ If you find this project useful, please consider citing:
journal={arXiv:2401.10891},
year={2024},
}
```
```