做乒乓球网站的图片,紫光华宇拼音输入法官方下载,做网站建设平台,the7 wordpress哪个好Depth Anything V2 复现 一、配置环境二、准备数据1. 权重文件2. 训练数据 三、Test四、Train 代码#xff1a;https://github.com/DepthAnything/Depth-Anything-V2 一、配置环境
在本机电脑win跑之后依旧爆显存#xff0c;放到服务器跑#xff1a;Ubuntu22.04#xff0c… Depth Anything V2 复现 一、配置环境二、准备数据1. 权重文件2. 训练数据 三、Test四、Train 代码https://github.com/DepthAnything/Depth-Anything-V2 一、配置环境
在本机电脑win跑之后依旧爆显存放到服务器跑Ubuntu22.04CUDA17
conda create -n DAv2 python3.10
conda activate DAv2conda下安装cuda。由于服务器上面我不能安装CUDA只能在conda上安装cuda。我安装的cuda11.7。 跟着下面的教程做 conda虚拟环境中安装cuda和cudnn再也不用头疼版本号的问题了 wget https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/linux-64/cudatoolkit-11.7.1-h4bc3d14_13.conda
conda install --use-local cudatoolkit-11.7.1-h4bc3d14_13.conda
wget https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/linux-64/cudnn-8.9.7.29-hcdd5f01_2.conda
conda install --use-local cudnn-8.9.7.29-hcdd5f01_2.conda安装其他依赖 记得在requirements.txt中增加tensorboard、h5py
pip install torch2.0.1cu117 torchvision0.15.2cu117 torchaudio2.0.2 -f https://download.pytorch.org/whl/torch_stable.html
pip install -r requirements.txt检查torch是否安装正确以及cuda版本
python
import torch
torch.cuda.is_available()
torch.version.cuda二、准备数据
1. 权重文件 将pre-trained-models放在 DepthAnythingV2/checkpoints 文件夹 2. 训练数据
训练的时候需要我这里之前就准备了vkitti。我先用vkitti数据跑一下试一下。
三、Test
Running script on images
python run.py \--encoder vits | vitb | vitl | vitg \--img-path path --outdir outdir \[--input-size size] [--pred-only] [--grayscale]Options: –img-path: You can either 1) point it to an image directory storing all interested images, 2) point it to a single image, or 3) point it a text file storing all image paths.–input-size (optional): By default, we use input size 518 for model inference. You can increase the size for even more fine-grained results.–pred-only (optional): Only save the predicted depth map, without raw image.–grayscale (optional): Save the grayscale depth map, without applying color palette. For example:
python run.py --encoder vitl --img-path assets/examples --outdir depth_visRunning script on videos
python run_video.py \--encoder vits | vitb | vitl | vitg \--video-path assets/examples_video --outdir video_depth_vis \[--input-size size] [--pred-only] [--grayscale]Our larger model has better temporal consistency on videos.
四、Train
根据自己的数据修改DepthAnythingV2/metric_depth/dataset/splits和train.py中的路径数据
sh dist_train.sh但我运行不了这个sh文件所以我选择直接配置.vscode/launch.json。并且我将我的train代码改为了非分布式的。
{// 使用 IntelliSense 了解相关属性。 // 悬停以查看现有属性的描述。// 欲了解更多信息请访问: https://go.microsoft.com/fwlink/?linkid830387version: 0.2.0,configurations: [{name: Python 调试程序: train.py,type: debugpy,request: launch,program: ${workspaceFolder}/metric_depth/train.py,console: integratedTerminal,args: [--epoch, 120,--encoder, vitl,--bs, 2,--lr, 0.000005,--save-path, ./exp/vkitti,--dataset, vkitti,--img-size, 518,--min-depth, 0.001,--max-depth, 20,--pretrained-from, ./checkpoints/depth_anything_v2_vitl.pth, ],env: {MASTER_ADDR: localhost,MASTER_PORT: 20596}},{name:Python 调试程序: run.py,type: debugpy,request: launch,program: ${workspaceFolder}/run.py,console: integratedTerminal,args: [--encoder, vitl,--img-path, assets/examples,--outdir, output/depth_anything_v2_vitl_test,--checkpoints,checkpoints/depth_anything_v2_vitl_test.pth],}]
}
