Search
This page is based on the one of RPZ course.
This setup is recommended by Dmytro Mishkin 1. Install Miniconda, Python version 3.X. 2. Run conda CLI. 3. Run
git clone https://gitlab.fel.cvut.cz/mishkdmy/mpv-python-assignment-templates conda create --name mpv-assignments-cpu-only python=3.8 conda activate mpv-assignments-cpu-only pip3 install torch==1.8.2+cpu torchvision==0.9.2+cpu -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html pip3 install kornia==0.6.3 tqdm notebook matplotlib opencv-contrib-python==4.5.3.56 seaborn tensorboard tensorboardX pip3 install kornia_moons --no-deps conda install -c conda-forge widgetsnbextension conda install -c conda-forge ipywidgets
For the GPU setup, if you have CUDA-capable GPU, run the following:
git clone https://gitlab.fel.cvut.cz/mishkdmy/mpv-python-assignment-templates conda create --name mpv-assignments-gpu python=3.8 conda activate mpv-assignments-gpu pip3 install torch==1.8.2+cu102 torchvision==0.9.2+cu102 -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html pip3 install kornia==0.6.3 tqdm notebook matplotlib opencv-contrib-python==4.5.3.56 seaborn tensorboard tensorboardX pip3 install kornia_moons --no-deps conda install -c conda-forge widgetsnbextension conda install -c conda-forge ipywidgets
4. a) Activate the environment with
conda activate mpv-assignments-cpu-only
PyCharm jupyter environment is buggy and not recommended. You still can use IDE to edit .py files though. It's best to use jupyter-notebook, google colab or jupyter-lab to work with jupyter notebooks, especially interactive ones (as in Correspondences and Tracking blocks.
It is possible to do all the work in cloud Google Colab without installing anything. You would need to have Google account though.
!pip install kornia==0.6.3