27cc439d01
* update config with predefined variables * rm redun Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * add test for config Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * support all types Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * newline at the end Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * update Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * extract code into a function and add docs Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * fix and add tests Signed-off-by: lixuanyi <lixuanyi@sensetime.com> * add unit tests and fix * fix * fix minor * fix test
Introduction
MMCV is a foundational python library for computer vision research and supports many research projects in MMLAB, such as MMDetection and MMAction.
It provides the following functionalities.
- Universal IO APIs
- Image/Video processing
- Image and annotation visualization
- Useful utilities (progress bar, timer, ...)
- PyTorch runner with hooking mechanism
- Various CNN architectures
- High-quality implementation of common CUDA ops
See the documentation for more features and usage.
Note: MMCV requires Python 3.6+.
Installation
Try and start with
pip install mmcv
or install from source
git clone https://github.com/open-mmlab/mmcv.git
cd mmcv
pip install -e .
If you are on macOS, replace the last command with
CC=lang CXX=clang++ CFLAGS='-stdlib=libc++' pip install -e .
Note that the building process may take up to 10 mins. We also provide pre-built mmcv with corresponding Pytorch and CUDA versions to simplify the building.
| CUDA | torch 1.5 | torch 1.4 | torch 1.3 |
|---|---|---|---|
| 10.2 | install | ||
| 10.1 | install | install | install |
| 10.0 | |||
| 9.2 | install | install | install |
| cpu | install | install | install |
Note: If you would like to use opencv-python-headless instead of opencv-python,
e.g., in a minimum container environment or servers without GUI,
you can first install it before installing MMCV to skip the installation of opencv-python.