- Linux or macOS (Windows is in experimental support)
- Python 3.7+
- PyTorch 1.8+
- CUDA 10.2+
I ran experiments with PyTorch 2.0.1, CUDA 11.7, Python 3.8, and Ubuntu 20.04. Other settings that satisfact the requirement would work.
You can simply follow our settings:
Use Anaconda to create a conda environment:
conda create -n mmdepth python=3.8
conda activate mmdepth
Install Pytorch following official instructions, e.g.,
conda install pytorch==2.0.1 torchvision==0.15.2 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install -U openmim
mim install mmengine
mim install "mmcv>=2.0.0"
If you develop and run mmdepth directly, install it from source:
git clone -b main https://github.com/RuijieZhu94/mmdepth.git
cd mmdepth
pip install -v -e .
# '-v' means verbose, or more output
# '-e' means installing a project in editable mode,
# thus any local modifications made to the code will take effect without reinstallation.
If training, you should install the tensorboard:
pip install future tensorboard
More information about installation can be found in docs of MMSegmentation (see get_started.md).