109 Star 876 Fork 1.5K

MindSpore/models

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README

Contents

TINY-SAM Description

We first propose a full-stage knowledge distillation method with online hard prompt sampling strategy to distill a lightweight student model. We also adapt the post-training quantization to the promptable segmentation task and further reducing the computational cost. Moreover, a hierarchical segmenting everything strategy is proposed to accelerate the everything inference by with almost no performance degradation. With all these proposed methods, our TinySAM leads to orders of magnitude computational reduction and pushes the envelope for efficient segment anything task. Extensive experiments on various zero-shot transfer tasks demonstrate the significantly advantageous performance of our TinySAM against counterpart methods.

Framework

The proposed framework and zero-shot instance segmentation results are shown below:

tinysam

Environment Requirements

Script description

Script and sample code


SNN-MLP
├── demo.py # demo entry
├── fig
│   ├── picture1.jpg # demo picture
│   └── tinysam.png # the illustration of the framework of tinysam
├── README.md # Readme
└── tinysam # source code of tinySAM

Eval process

Usage

After installing MindSpore via the official website, you can start evaluation as follows:

Download

Download ckpts from modelzoo.

Launch


# infer example
  python demo.py #CPU

ModelZoo Homepage

Please check the official homepage.

马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/mindspore/models.git
git@gitee.com:mindspore/models.git
mindspore
models
models
master

搜索帮助