Computer Vision models for "What Is That" task in RoboCup@Home 2022
ref : https://www.augmentedstartups.com/YOLOR-You-Only-Learn-One-Representation-PyTorch
- create conda environment using python 3.9.6
- Install pytorch
$ pip install torch==1.9.0+cu111 torchvision==0.10.0+cu111 torchaudio===0.9.0 -f https://download.pytorch.org/whl/torch_stable.html
- Install Cython
$ pip install -U cython
- Install pycocotool
$ pip install "git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI"
- Download yolor config folder from https://drive.google.com/file/d/17JveNhnGDXN2ilw_lLpfy6XLt7nj-sjd/view
- Put all downloaded files to /object_detection_module/config
- Install requirement.txt
pip install -r requirements.txt