Skip to content

Latest commit

 

History

History
62 lines (45 loc) · 1.86 KB

INSTALL.md

File metadata and controls

62 lines (45 loc) · 1.86 KB
Raw

Installation

Most of the requirements of this projects are exactly the same as maskrcnn-benchmark. If you have any problem of your environment, you should check their issues page first. Hope you will find the answer.

Requirements:

  • PyTorch >= 1.4
  • torchvision >= 0.4
  • cocoapi
  • yacs
  • matplotlib
  • GCC >= 4.9
  • OpenCV

Step-by-step installation

# first, make sure that your conda is setup properly with the right environment
# for that, check that `which conda`, `which pip` and `which python` points to the
# right path. From a clean conda env, this is what you need to do

conda create -y --name pysgg
conda activate pysgg

# this installs the right pip and dependencies for the fresh python
conda install -y ipython scipy h5py

# scene_graph_benchmark and coco api dependencies
pip install ninja yacs cython matplotlib tqdm opencv-python overrides gpustat gitpython ipdb graphviz tensorboardx termcolor scikit-learn==0.23.1

# follow PyTorch installation in https://pytorch.org/get-started/locally/
conda install pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 -c pytorch

export INSTALL_DIR=$PWD

# install pycocotools
cd $INSTALL_DIR
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
python setup.py build_ext install

# install apex
cd $INSTALL_DIR
git clone https://github.com/NVIDIA/apex.git
cd apex
git checkout f37fdf07367a71521bd14fec66153e0996ad128c
python setup.py install --cuda_ext --cpp_ext

# install PyTorch Detection
cd $INSTALL_DIR
git clone https://github.com/KaihuaTang/Scene-Graph-Benchmark.pytorch.git
cd pysgg

# the following will install the lib with
# symbolic links, so that you can modify
# the files if you want and won't need to
# re-build it
python setup.py build develop


unset INSTALL_DIR