ed2887bb72
* Support to specify LR of DCN's conv_offset * Resolve comments & add unit test * Resolve formats * Fix CI for DCN * Mock DCN when cpu only * Use mock for cpu testing * Fix docstring and support ModulatedDCN * set offset_lr_mult as dcn's arguments, link CU-49u01p * fix lr bug * fall back to set LR in constructor * resolve comments |
||
|---|---|---|
| .github/workflows | ||
| docs | ||
| examples | ||
| mmcv | ||
| tests | ||
| .dockerignore | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| .readthedocs.yml | ||
| CONTRIBUTING.md | ||
| Dockerfile | ||
| Jenkinsfile | ||
| LICENSE | ||
| MANIFEST.in | ||
| README.md | ||
| requirements.txt | ||
| setup.cfg | ||
| setup.py | ||
README.md
Introduction
MMCV is a foundational python library for computer vision research and supports many research projects as below:
- MMDetection: Detection toolbox and benchmark
- MMDetection3D: General 3D object detection toolbox and benchmark
- MMSegmentation: Semantic segmentation toolbox and benchmark
- MMEditing: Image and video editing toolbox
- MMPose: Pose estimation toolbox and benchmark
- MMAction2: Action understanding toolbox and benchmark
- MMClassification: Image classification toolbox and benchmark
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
There are two versions of MMCV:
- mmcv: lite, without CUDA ops but all other features, similar to mmcv<1.0.0. It is useful when you do not need those CUDA ops.
- mmcv-full: comprehensive, with full features and various CUDA ops out of box. It takes longer time to build.
Note: Do not install both versions in the same environment, otherwise you may encounter errors like ModuleNotFound. You need to uninstall one before installing the other.
Install with pip
a. Install the lite version.
pip install mmcv
b. Install the full version.
Before installing mmcv-full, make sure that PyTorch has been successfully installed following the official guide.
We provide pre-built mmcv packages (recommended) with different PyTorch and CUDA versions to simplify the building.
| CUDA | torch 1.6 | torch 1.5 | torch 1.4 | torch 1.3 |
|---|---|---|---|---|
| 10.2 | install |
install |
||
| 10.1 | install |
install |
install |
install |
| 9.2 | install |
install |
install |
install |
| cpu | install |
install |
install |
install |
Another way is to compile locally by running
pip install mmcv-full
Note that the local compiling may take up to 10 mins.
Install from source
After cloning the repo with
git clone https://github.com/open-mmlab/mmcv.git
cd mmcv
You can either
-
install the lite version
pip install -e . -
install the full version
MMCV_WITH_OPS=1 pip install -e .
If you are on macOS, add the following environment variables before the installing command.
CC=clang CXX=clang++ CFLAGS='-stdlib=libc++'
e.g.,
CC=clang CXX=clang++ CFLAGS='-stdlib=libc++' MMCV_WITH_OPS=1 pip install -e .
If you are on Windows10, set the following environment variable before the installing command.
set MMCV_WITH_OPS=1
e.g.,
set MMCV_WITH_OPS=1
pip install -e .
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.
TroubleShooting
If you meet issues when running or compiling mmcv, we list some common issues in TROUBLESHOOTING.md.