Skip to content

Instantly share code, notes, and snippets.

@hellock

hellock/mmdetection_env.sh

Last active December 20, 2020 22:58
Show Gist options
  • Star 8 You must be signed in to star a gist
  • Fork 4 You must be signed in to fork a gist
  • Save hellock/bf23cd7348c727d69d48682cb6909047 to your computer and use it in GitHub Desktop.
Save hellock/bf23cd7348c727d69d48682cb6909047 to your computer and use it in GitHub Desktop.
Download ZIP
Setup mmdetection with conda
Raw
mmdetection_env.sh
conda create -n open-mmlab python=3.7 -y
source activate open-mmlab
conda install -c pytorch pytorch torchvision -y
conda install cython -y
git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection
pip install -v -e .
mkdir data
ln -s $COCO_ROOT data
@Clark1216
Copy link

Does Last cmd line has an error?
ln: failed to create symbolic link './data': File exists

@zhihongp
Copy link

zhihongp commented Dec 9, 2019

That's either create a new data folder or link an existing one I guess, so no need to run the last two lines together

@dsuess
Copy link

dsuess commented May 6, 2020

We are currently testing a ready-built version (+ dependencies) on our conda channel: https://anaconda.org/silverpond

@SunilPadikar
Copy link

These two lines failed. Could you please help me with that.

mkdir data
ln -s $COCO_ROOT data

Where is $COCO_ROOT defined?

@dsuess
Copy link

dsuess commented Dec 20, 2020

You need to set $COCO_ROOT to the path to the COCO dataset on your machine (that's assuming you want to train on COCO)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment