Skip to content

Latest commit

 

History

History
34 lines (24 loc) · 521 Bytes

INSTALL.md

File metadata and controls

34 lines (24 loc) · 521 Bytes

Installation

Step 1: Clone this repo

git clone https://github.com/SHI-Labs/VMFormer

Step 2: Create conda environment

conda create --name vmformer python=3.7
conda activate vmformer

Step 3: Install pytorch and torchvision

conda install pytorch==1.9.0 torchvision==0.10.0 -c pytorch

Step 4: Install dependencies

pip install -r requirements.txt

Step 5: Install CUDA version of MultiScaleDeformableAttention

cd ./models/ops
sh ./make.sh
python test.py