0. install miniconda
1. create conda env
$ conda create -y -n cvt python=3.8
2. activate created env
$ source activate cvt
3. install pytorch through pip
$ pip install torch==1.11+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html
$ $ pip install torch==1.11+cu113 torchvision==0.12.0+cu113 -f https://download.pytorch.org/whl/torch_stable.html
$ pip install torch=1.11.0+cu113 torchvision=0.12.0+cu113 --extra-index-url https://download.pytorch.org/whl/cu113
4. Install opencv
$ (optional) python -m pip install --upgrade pip
$ python -m pip install opencv-python
5. install others
$ pip install tqdm matplotlib pyquaternion scipy nuscenes-devkit scikit-image fvcore torchmetrics einops
6. compiling CUDA operators
$ cd ./models/ops
$ sh ./make.sh
$ python test.py # unit test (should see all checking is True)
7. compliing CUDA operators - 2
$ cd ./models/tbpformer/kernels/window_process
$ python setup.py install
'개인' 카테고리의 다른 글
BEVFormer Code Analysis (0) | 2023.05.24 |
---|---|
학문을 직업으로 삼으려는 젊은 학자들을 위하여 (0) | 2019.12.18 |