/828-A3

Primary LanguagePythonMIT LicenseMIT

Installation Instructions

  • conda create --name mask2former python=3.8 -y
  • conda activate mask2former
  • conda install pytorch==1.9.0 torchvision==0.10.0
  • cudatoolkit=11.1 -c pytorch -c nvidia
  • pip install -U opencv-python

under your working directory

To Test:

  • Download the checkpoints from here and place them in ckpt(have to create this) directory in Mask2Former directory.
  • python test.py path2imageDir path2annotationDir 1 #for question1

Output json is stored in ./output directory (gets overwritten)

  • python test.py path2imageDir path2annotationDir 2 #for question2