Skip to content

Latest commit

 

History

History
46 lines (39 loc) · 1.64 KB

INSTALL.md

File metadata and controls

46 lines (39 loc) · 1.64 KB
Raw

Installation

Requirements

  • Linux or macOS with Python ≥ 3.6
  • PyTorch ≥ 1.9 and torchvision that matches the PyTorch installation. Install them together at pytorch.org to make sure of this. Note, please check PyTorch version matches that is required by Detectron2.
  • Detectron2: follow Detectron2 installation instructions.
  • OpenCV is optional but needed by demo and visualization
  • pip install -r requirements.txt

CUDA kernel for MSDeformAttn

After preparing the required environment, run the following command to compile CUDA kernel for MSDeformAttn:

CUDA_HOME must be defined and points to the directory of the installed CUDA toolkit.

cd fcclip/modeling/pixel_decoder/ops
sh make.sh

Building on another system

To build on a system that does not have a GPU device but provide the drivers:

TORCH_CUDA_ARCH_LIST='8.0' FORCE_CUDA=1 python setup.py build install

Example conda environment setup

conda create --name fcclip python=3.8 -y
conda activate fcclip
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
git clone https://github.com/facebookresearch/detectron2.git
python -m pip install -e detectron2
pip install git+https://github.com/cocodataset/panopticapi.git
pip install git+https://github.com/mcordts/cityscapesScripts.git
git clone https://github.com/bytedance/fcclip.git
cd fcclip
pip install -r requirements.txt
cd fcclip/modeling/pixel_decoder/ops
sh make.sh
cd ../../../..