Skip to content

Files

Latest commit

 Cannot retrieve latest commit at this time.

History

History
34 lines (22 loc) · 929 Bytes

INSTALL.md

File metadata and controls

34 lines (22 loc) · 929 Bytes

Installation

The code was tested on Ubuntu 16.04, with Anaconda Python 3.6 and PyTorch v1.5.0. NVIDIA GPUs are needed for both training and testing. After install Anaconda:

  1. Install pytorch1.5.0:

  2. Install COCOAPI:

    # COCOAPI=/path/to/clone/cocoapi
git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
cd $COCOAPI/PythonAPI
make
python setup.py install --user

  3. Install the requirements and clone this repo

    pip install -r requirements.txt
git clone --recursive https://github.com/PingoLH/CenterNet-HarDNet.git

  4. [Optional, only required if you are using extremenet or multi-scale testing] Compile NMS if your want to use multi-scale testing or test ExtremeNet.

    cd $CenterNet_ROOT/src/lib/external
make