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

Installation

测试过的python版本：3.8,3.10
官方步骤：

1
2
3
4
5
6
7
8

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

1
2
3
4
5

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/" # `/usr/include`for missing `crypt.h`
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

1
2
3
4
5
6
7
8
9
10
11
12

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++

# 找不到crypt.h的情况
sudo pacman -S libxcrypt-compat

export CXXFLAGS="${CXXFLAGS} -fuse-ld=/usr/bin/ld"

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
2

pip install gradio==3.37.0
pip install matplotlib==3.7.0

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

需要解决的问题

同level下mask重合

Part-seg-dataset Generation

效果

原图：

Instance identification:

Part segmentation

Overview of the proposed SceneGraphFusion framework. Our method takes a stream of RGB-D images a) as input to create an incremental geometric segmentation b). Then, the properties of each segment and a neighbor graph between segments are constructed. The properties d) and neighbor graph e) of the segments that have been updated in the current frame c) are used as the inputs to compute node and edge features f) and to predict a 3D scene graph g). Finally, the predictions are h) fused back into a globally consistent 3D graph.

这片文章可以成为场景物理重建的基石之一
类似的后续工作有OMG-Seg

是什么

通用图像分割模型，以实现细分并识别任何所需粒度的任何内容

• Semantic-awareness
• Granularity-abundance

数据集

注：此DINO并非自蒸馏自监督的那个[[DINO]]，而是派生自[[DETR]]

A vision-language model that unifies vision-language understanding and generation tasks.

主要分为两块工作：

• 去除图文检索所使用的数据集中的噪声
• vision language understanding and generation

Model

Noise Filtering

Understanding & Generation

将不同帧$X_t$中的特征集合在M中特征点的公式：

https://github.com/IDEA-Research/Grounded-Segment-Anything

By [[Grounding-DINO]] + SAM
Achieving Open-Vocab. Det & Seg