Skip to content

Latest commit

 

History

History
82 lines (58 loc) · 1.49 KB

VOS_SETUP.md

File metadata and controls

82 lines (58 loc) · 1.49 KB

Setup

Install requirements

  • Linux or MacOS
  • Python >= 3.5
  • GCC >= 4.9
git clone https://github.com/MegviiDetection/video_analyst.git
cd video_analyst

You can choose either using native python (with pip/pip3) or using virtual environment (with conda).

pip3 install -U -r requirements.txt

python-tkinter

In case of:

ModuleNotFoundError: No module named 'tkinter'

Please install python3-tk by running:

sudo apt-get install python3-tk

Download models & raw results

Compile evaluation toolkit

bash compile.sh

Set datasets

Download Davis Set soft link to dataset directory

ln -s path_to_datasets datasets/DAVIS

At path_to_datasets:

datasets
└── DAVIS
    ├── Annotations
    |        ├── 480p # annotation for davis2017
    |        └── 480p_2016 # annotation for davis2016
    ├── ImageSets
    └── ...

Set models

Set soft link to model directory

ln -s path_to_models models/sat

At path_to_models:

models
├── sat
    |── transferred-model
       ├── siamfcpp_brain2torch-md5_abfe30e8531e001d83e9f0a6482da444.pkl
       ├── sat_res50_brain2torch-davis17-md5_1170502f6b4062399b19658aeafa9474.pkl