Posted 2025-04-22Updated 2025-05-03Note4 minutes read (About 563 words)

Official repo:
https://github.com/liuhengyue/fcsgg
Our repo:
https://github.com/PSGBOT/KAF-Generation

Installation

Environment Preparation

git clone git@github.com:liuhengyue/fcsgg.git
cd fcsgg
git submodule init
git submodule update
conda create --name fcsgg
conda create -n fcsgg python=3.10
conda install nvidia/label/cuda-11.8.0::cuda-toolkit -c nvidia/label/cuda-11.8.0
conda install cudatoolkit
pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118

# for building detectron
conda install -c conda-forge gcc=11.2.0
conda install -c conda-forge gxx=11.2.0

conda env config vars set LD_LIBRARY_PATH="/home/cyl/miniconda3/envs/fcsgg/lib/"
conda env config vars set CPATH="/home/cyl/miniconda3/envs/fcsgg/include/"
conda env config vars set CUDA_HOME="/home/cyl/miniconda3/envs/fcsgg/"

conda deactivate
conda activate fcsgg

export CC=$CONDA_PREFIX/bin/gcc
export CXX=$CONDA_PREFIX/bin/g++

pip install -r requirements.txt
python -m pip install -e detectron2

Downloads

Datasets:

cd ~/Reconst
wget https://cs.stanford.edu/people/rak248/VG_100K_2/images.zip -P ./Data/vg/
wget https://cs.stanford.edu/people/rak248/VG_100K_2/images2.zip -P ./Data/vg/
unzip -j ./Data/vg/images.zip -d ./Data/vg/VG_100K
unzip -j ./Data/vg/images2.zip -d ./Data/vg/VG_100K

Download the scene graphs and extract them to datasets/vg/VG-SGG-with-attri.h5.

Issues

1

1	AttributeError: module 'PIL.Image' has no attribute 'LINEAR'. Did you mean: 'BILINEAR'?

LINEAR-> BILINEAR: commit

2

在尝试训练的过程中报错：

1
2
3

  File "/home/cyl/Reconst/fcsgg/fcsgg/data/detection_utils.py", line 432, in generate_score_map
    masked_fmap = torch.max(masked_fmap, gaussian_mask * k)
RuntimeError: The size of tensor a (55) must match the size of tensor b (56) at non-singleton dimension 1

modify detection_utils.py: commit

Training

首先更改训练的配置文件./config/quick_schedules/Quick-FCSGG-HRNet-W32.yaml, (原文件使用预训练的参数)

MODEL:
  META_ARCHITECTURE: "CenterNet"
  HRNET:
    WEIGHTS: "output/FasterR-CNN-HR32-3x.pth"

更改为train from scratch

MODEL:
  META_ARCHITECTURE: "CenterNet"
  HRNET:
    WEIGHTS: ""  # Empty string to train from scratch

再运行：

1	python tools/train_net.py --num-gpus 1 --config-file configs/quick_schedules/Quick-FCSGG-HRNet-W32.yaml

成功训练✌

...
[04/23 10:21:01] d2.utils.events INFO:  eta: 0:05:37  iter: 1159  total_loss: 1.042  loss_cls: 0.7593  loss_box_wh: 0.08827  loss_center_reg: 0.02485  loss_raf: 0.1754    time: 0.4042  last_time: 0.4519  data_time: 0.0043  last_data_time: 0.0044   lr: 0.001  max_mem: 4141M
[04/23 10:21:09] d2.utils.events INFO:  eta: 0:05:29  iter: 1179  total_loss: 1.028  loss_cls: 0.7208  loss_box_wh: 0.09246  loss_center_reg: 0.02669  loss_raf: 0.1625    time: 0.4042  last_time: 0.4035  data_time: 0.0041  last_data_time: 0.0044   lr: 0.001  max_mem: 4141M
[04/23 10:21:17] d2.utils.events INFO:  eta: 0:05:21  iter: 1199  total_loss: 1.01  loss_cls: 0.671  loss_box_wh: 0.1038  loss_center_reg: 0.02432  loss_raf: 0.1635    time: 0.4042  last_time: 0.3943  data_time: 0.0042  last_data_time: 0.0043   lr: 0.001  max_mem: 4141M
[04/23 10:21:25] d2.utils.events INFO:  eta: 0:05:13  iter: 1219  total_loss: 0.9737  loss_cls: 0.6887  loss_box_wh: 0.0929  loss_center_reg: 0.02574  loss_raf: 0.1749    time: 0.4041  last_time: 0.4101  data_time: 0.0041  last_data_time: 0.0042   lr: 0.001  max_mem: 4141M
...

Explanation

Posted 2025-03-24Updated 2025-05-03Note3 minutes read (About 444 words)

Semantic-SAM Repository Application

My repository: https://github.com/Chen-Yulin/Semantic-SAM

Installation

官方步骤：

pip3 install torch==1.13.1 torchvision==0.14.1 --extra-index-url https://download.pytorch.org/whl/cu113
python -m pip install 'git+https://github.com/MaureenZOU/detectron2-xyz.git'
pip install git+https://github.com/cocodataset/panopticapi.git
git clone https://github.com/UX-Decoder/Semantic-SAM
cd Semantic-SAM
python -m pip install -r requirements.txt

export DATASET=/pth/to/dataset  # path to your coco data

一些绊脚石 ^ ^

1

根据[[Cuda+Torch]]，需要先安装cudatoolkit和cuda-toolkit

conda install nvidia/label/cuda-11.7.0::cuda-toolkit -c nvidia/label/cuda-11.7.0 
conda install cudatoolkit # no need to specify version
conda env config vars set LD_LIBRARY_PATH="/home/cyl/miniconda3/envs/<name>/lib/"
conda env config vars set CPATH="/home/cyl/miniconda3/envs/<name>/include/"
conda env config vars set CUDA_HOME="/home/cyl/miniconda3/envs/<name>/"

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

2

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

conda install -c conda-forge gcc=11.2.0
conda install -c conda-forge gxx=11.2.0

# 指定编译器路径
export CC=$CONDA_PREFIX/bin/gcc
export CXX=$CONDA_PREFIX/bin/g++

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 ^ ^

3

安装完成后直接import semantic_sam会报错ModuleNotFoundError: No module named 'MultiScaleDeformableAttention' ^ ^
提示：

1
2
3

Please compile MultiScaleDeformableAttention CUDA op with the following commands:
	`cd mask2former[/modeling/pixel_decoder/ops](http://127.0.0.1:8888/modeling/pixel_decoder/ops)`
	`sh make.sh`

需要手动make一下 Mask2Former:

1 2	cd Mask2Former/mask2former/modeling/pixel_decoder/ops/ sh make.sh

4

一些版本问题

1	pip install gradio==3.37.0

Demo 🐱

Generate multi-granularity Mask on CLICK

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。

Automatically Generate Mask on Different Granularity

1	python demo_auto_generation.py --ckpt ./weights/swinl_only_sam_many2many.pth

Posted 2023-05-10Updated 2025-05-03a few seconds read (About 8 words)

Git Basics

Game

learning git branch

Posted 2023-05-10Updated 2025-05-03Notea few seconds read (About 83 words)

Git Merge

Git Merge
- Solve conflict
  - Tools
  - Commands

Solve conflict

Tools

In nvim, I use plugin fugitive

Commands

open two vertical buffer (one form target, another from feature)

1	:Gvdiffsplit!

stay on middle and use

1	:diffget [buffername](local)

OR
go to target/feature buffer and use

1	:diffput [buffername](target/feature)

save the local file and use

1 2	:Git add . :Git commit -m "solve merge conflicts"

Posted 2023-05-10Updated 2025-05-03a few seconds read (About 86 words)

Git Repository

Add remote repository
Branch

Add remote repository

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.

Branch

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]

Posted 2023-05-10Updated 2025-05-03a minute read (About 202 words)

Git Submodule

What is a Git submodule?

A Git submodule allows a user to include a Git repository as a subdirectory of another Git repository. This can be useful when a project needs to include and use another project. For example, it may be a third-party library or a library developed independently for use in multiple parent projects. With submodules, these libraries can be managed as independent projects while being used in the user’s project. This allows for better organization and management of the code.

How to add a submodule to a project

To add an existing Git repository as a submodule to a project, the git submodule add command can be used. The command format is git submodule add <url> <path>, where <url> is the URL of the submodule repository and <path> is the storage path of the submodule in the project. For example, if a user wants to add the remote repository https://github.com/username/repo.git as a submodule to their project and store it in the my-submodule directory, they can use the following command:

1	git submodule add https://github.com/username/repo.git my-submodule

This will successfully add a submodule named my-submodule to the user’s project.

Posted 2023-05-10Updated 2025-05-03a minute read (About 217 words)

Git Version

check commit history
change version
switch to latest
need a early version of a repository

check commit history

1 2	git log git log --pretty=oneline

commit 0637340f4d8d288a8d24dd5193855c9e5def776d (HEAD -> main, origin/main, origin/HEAD)
Author: Chen-Yulin <chenyulin@sjtu.edu.cn>
Date:   Tue Mar 21 20:55:16 2023 +0800

    modify obsidian dir

commit dde357abf53f26972bd3ad0e1b1e840412b26fc7
Author: Chen-Yulin <chenyulin@sjtu.edu.cn>
Date:   Tue Mar 21 20:54:57 2023 +0800

    modify obsidian dir

commit 089578f74d206c7fbb503a293d34edf878dad3f3
Author: Chen-Yulin <chenyulin@sjtu.edu.cn>
Date:   Tue Mar 21 20:34:09 2023 +0800

    fix plugin compatibility

commit b62c94796b757851a5e8f38925f28b160a8bf4f0
Author: Chen-Yulin <chenyulin@sjtu.edu.cn>
Date:   Tue Mar 21 14:59:02 2023 +0800

change version

1	git reset --hard [version hash]

switch to latest

git pull

or locally

1	git checkout master

need a early version of a repository

Fork the latest repository on Github

clone the forked repository

1	git clone ...

change the version locally and push

git log
...
git reset --hard [version hash]
git push --force

Installation

Environment Preparation

Downloads

Issues

1

2

Training

Explanation

Installation

一些绊脚石 ^ ^

1

2

3

4

Demo 🐱

Generate multi-granularity Mask on CLICK

Automatically Generate Mask on Different Granularity

Game

Git Merge

Solve conflict

Tools

Commands

Add remote repository

Branch

What is a Git submodule?

How to add a submodule to a project

check commit history

change version

switch to latest

need a early version of a repository

Fork the latest repository on Github

clone the forked repository

change the version locally and push

Archives

Recents

Tags