Repository:
official:
1 | conda env create -f conda.yaml |
不建议使用official的conda.yaml, 使用更改后的conda_cyl.yaml。
1 | pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1 |
官方提供了 depth estimation 和 segmentation 的 notebook，可以找时间理解一下
使用的数据集为Imagenet-mini
1 | imagenet-mini |
Note: 需要额外添加一个label.txt
使用脚本生产数据集的meta data:
1 |
Semantic-SAM Repository Application
My repository: https://github.com/Chen-Yulin/Semantic-SAM
官方步骤：
1 | pip3 install torch==1.13.1 torchvision==0.14.1 --extra-index-url https://download.pytorch.org/whl/cu113 |
根据[[Cuda+Torch]]，需要先安装cudatoolkit和cuda-toolkit
1 | conda install nvidia/label/cuda-11.7.0::cuda-toolkit -c nvidia/label/cuda-11.7.0 |
然后按照torch官网的安装指令：
1 | conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia |
第二行直接运行可能会报错，提示系统gcc版本过高，安装gcc=11.2.0
1 | conda install -c conda-forge gcc=11.2.0 |
如果编译时出现ld: cannot find -lcudart: No such file or directory collect2: error: ld returned 1 exit status 报错，只是因为没有安装cudatoolkit ^ ^
安装完成后直接import semantic_sam会报错ModuleNotFoundError: No module named 'MultiScaleDeformableAttention' ^ ^
提示：
1 | Please compile MultiScaleDeformableAttention CUDA op with the following commands: |
需要手动make一下 Mask2Former:
1 | cd Mask2Former/mask2former/modeling/pixel_decoder/ops/ |
一些版本问题
1 | pip install gradio==3.37.0 |
1 | python demo.py --ckpt ./weights/swinl_only_sam_many2many.pth |
Comment: 效果相较于SAM更多体现了语义的一致性，而不是基于texture进行分割。
1 | python demo_auto_generation.py --ckpt ./weights/swinl_only_sam_many2many.pth |
1 | git remote add origin git@github.com:... |
origin is the name of the repository
Check remote repository settings:
1 | git remote -v |
Before push to remote repository, make sure the branch name is the same.
find all the branch
1 | git branch -a |
find all the branch on remote repository
1 | git remote -r |
Rename
1 | git branch -m oldBranchName newBranchName |
Move to branch:
1 | git checkout [branchname/SHA-1] |
File Path: catkin_ws/src/test/script/env_pkl_generator.py
1 | cd ~ |
It will open Gazebo and RViz and display the robotic arm on both sofware.
1 | cd ~ |
向日葵
识别吗
341 866 266
ge6v9Q
