Skip to content

Latest commit

 

History

History
47 lines (24 loc) · 1.46 KB

README.md

File metadata and controls

47 lines (24 loc) · 1.46 KB

visu-segment-anything

visualisation of the product of segment-anything

First install :

use the script amg.py in the directory scripts on this image :

image

You will have this result with the masked images ( black /white ) in the directory : image

to install maskimg , you need pip install python-opencv jinja2 numpy

#use maskimg.py:

usage: maskimg.py [-h] [-f INPUTFILE] [-d INPUTDIR] [-o OUTPUT]

Script for processing input files and directories

options:
  -h, --help            show this help message and exit
  -f INPUTFILE, --inputfile INPUTFILE
                        Input file path
  -d INPUTDIR, --inputdir INPUTDIR
                        Input directory path
  -o OUTPUT, --output OUTPUT
                        Output path

The maskimg.py will give you this result in the output directory:

image

In the directory , a index.html will be created , so launch a http server IN THE DIRECTORY : python3 -m http.server 9000

3D mask threejs