Skip to content

Latest commit

 

History

History
185 lines (125 loc) · 6 KB

install.md

File metadata and controls

185 lines (125 loc) · 6 KB
Raw

Installation

Requirements

  • Linux (Windows is not officially supported)
  • Python 3.6+
  • PyTorch 1.5+
  • CUDA 9.2+
  • GCC 5+
  • mmcv 1.3.16+
  • mmdet 2.16.0+
  • mmseg 0.20.2+

Compatible MMCV, MMDetection and MMSegmentation versions are shown below. Please install the correct version of them to avoid installation issues.

MMSelfSup version MMCV version MMSegmentation version MMDetection version
master mmcv-full >= 1.3.16 mmseg >= 0.20.2+ mmdet >= 2.16.0+

Note: You need to run pip uninstall mmcv first if you have mmcv installed. If mmcv and mmcv-full are both installed, there will be ModuleNotFoundError.

Prepare environment

  1. Create a conda virtual environment and activate it.

    conda create -n openmmlab python=3.7 -y
conda activate openmmlab

  2. Install PyTorch and torchvision following the official instructions, e.g.,

    conda install pytorch torchvision -c pytorch

    Make sure that your compilation CUDA version and runtime CUDA version match. You can check the supported CUDA version for precompiled packages on the PyTorch website.

    E.g.1 If you have CUDA 10.1 installed under /usr/local/cuda and would like to install PyTorch 1.7, you need to install the prebuilt PyTorch with CUDA 10.1.

    conda install pytorch==1.7.0 torchvision==0.8.0 cudatoolkit=10.1 -c pytorch

    If you build PyTorch from source instead of installing the prebuilt package, you can use more CUDA versions such as 9.0.

Install MMSelfSup

  1. install mmcv-full

    pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/{cu_version}/{torch_version}/index.html

    Please replace {cu_version} and {torch_version} in the url to your desired one. For example, to install the latest mmcv-full with CUDA 11.0 and PyTorch 1.7.0, use the following command:

    pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu110/torch1.7.0/index.html

    See here for different versions of MMCV compatible to different PyTorch and CUDA versions.

    Optionally you can compile mmcv from source if you need to develop both mmcv and mmselfsup. Refer to the guide for details.

  2. Install MMSegmentation and MMDetection.

    You can simply install MMSegmentation and MMDetection with the following command:

    pip install mmsegmentation mmdet

    In addition to installing MMSegmentation and MMDetection by pip, user can also install them by mim.

    pip install openmim
mim install mmdet
mim install mmsegmentation

  3. Clone the mmselfsup repository and install.

    git clone https://github.com/open-mmlab/mmselfsup.git
cd mmselfsup
pip install -v -e .

Note:

a. When specifying -e or develop, MMSelfSup is installed on dev mode, any local modifications made to the code will take effect without reinstallation.

A from-scratch setup script

Here is a full script for setting up mmselfsup with conda.

conda create -n openmmlab python=3.7 -y
conda activate openmmlab

conda install -c pytorch pytorch torchvision -y

# install the latest mmcv
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.7.0/index.html

# install mmdetection mmsegmentation
pip install mmsegmentation mmdet

git clone https://github.com/open-mmlab/mmselfsup.git
cd mmselfsup
pip install -v -e .

Another option: Docker Image

We provide a Dockerfile to build an image.

# build an image with PyTorch 1.6.0, CUDA 10.1, CUDNN 7.
docker build -f ./docker/Dockerfile --rm -t mmselfsup:torch1.10.0-cuda11.3-cudnn8 .

Important: Make sure you've installed the nvidia-container-toolkit.

Run the following cmd:

docker run --gpus all --shm-size=8g -it -v {DATA_DIR}:/workspace/mmselfsup/data mmselfsup:torch1.10.0-cuda11.3-cudnn8 /bin/bash

{DATA_DIR} is your local folder containing all these datasets.

Verification

To verify whether MMSelfSup is installed correctly, we can run the following sample code to initialize a model and inference a demo image.

import torch

from mmselfsup.models import build_algorithm

model_config = dict(
    type='Classification',
    backbone=dict(
        type='ResNet',
        depth=50,
        in_channels=3,
        num_stages=4,
        strides=(1, 2, 2, 2),
        dilations=(1, 1, 1, 1),
        out_indices=[4],  # 0: conv-1, x: stage-x
        norm_cfg=dict(type='BN'),
        frozen_stages=-1),
    head=dict(
        type='ClsHead', with_avg_pool=True, in_channels=2048,
        num_classes=1000))

model = build_algorithm(model_config).cuda()

image = torch.randn((1, 3, 224, 224)).cuda()
label = torch.tensor([1]).cuda()

loss = model.forward_train(image, label)

The above code is supposed to run successfully upon you finish the installation.

Using multiple MMSelfSup versions

If there are more than one mmselfsup on your machine, and you want to use them alternatively, the recommended way is to create multiple conda environments and use different environments for different versions.

Another way is to insert the following code to the main scripts (train.py, test.py or any other scripts you run)

import os.path as osp
import sys
sys.path.insert(0, osp.join(osp.dirname(osp.abspath(__file__)), '../'))

Or run the following command in the terminal of corresponding root folder to temporally use the current one.

export PYTHONPATH="$(pwd)":$PYTHONPATH