34 lines
1.8 KiB
Plaintext
34 lines
1.8 KiB
Plaintext
《Depth Anything》
|
||
网址：https://github.com/LiheYoung/Depth-Anything
|
||
|
||
# 1. 配置
|
||
git clone https://github.com/LiheYoung/Depth-Anything
|
||
cd Depth-Anything
|
||
pip install -r requirements.txt、
|
||
|
||
# 2. 下载深度预训练模型
|
||
mkdir checkpoints # 新建文件夹
|
||
# Way1：有网络下载
|
||
from depth_anything.dpt import DepthAnything
|
||
encoder = 'vits' # can also be 'vitb' or 'vitl'
|
||
depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{:}14'.format(encoder))
|
||
encoder = 'vitb' # can also be 'vitb' or 'vitl'
|
||
depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{:}14'.format(encoder))
|
||
encoder = 'vitl' # can also be 'vitb' or 'vitl'
|
||
depth_anything = DepthAnything.from_pretrained('LiheYoung/depth_anything_{:}14'.format(encoder))
|
||
# Way2：无网络下载
|
||
https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vits14.pth
|
||
https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vits14.pth
|
||
https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitb14.pth
|
||
https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitb14.pth
|
||
https://huggingface.co/spaces/LiheYoung/Depth-Anything/blob/main/checkpoints/depth_anything_vitl14.pth
|
||
https://huggingface.co/spaces/LiheYoung/Depth-Anything/resolve/main/checkpoints/depth_anything_vitl14.pth
|
||
|
||
# 3.1. 基础使用方法
|
||
python run.py --encoder <vits | vitb | vitl> --img-path <img-directory | single-img | txt-file> --outdir <outdir> [--pred-only] [--grayscale]
|
||
|
||
python run_video.py --encoder <vits | vitb | vitl> --video-path assets/examples_video --outdir video_depth_vis
|
||
|
||
# 3.2. 进阶使用方法
|
||
python batch_process_and_compare_V1.py --img-path assets/examples
|