From 1f18ca9c2decff87873aeff03d4237a348c293d0 Mon Sep 17 00:00:00 2001 From: Haodong Duan <34324155+kennymckormick@users.noreply.github.com> Date: Fri, 21 May 2021 14:36:06 +0800 Subject: [PATCH] Update README.md --- README.md | 12 ++++-------- 1 file changed, 4 insertions(+), 8 deletions(-) diff --git a/README.md b/README.md index db57306..5ca60a2 100644 --- a/README.md +++ b/README.md @@ -430,17 +430,13 @@ MIM provides a unified API for launching and installing OpenMMLab projects and t -## Build custom projects with mim +## Build custom projects with MIM -We provide an example about how to build custom projects based on MM codebases -and mim. In `examples/custom_backbone`, we define a custom backbone and there -is a classification config file that uses the backbone. To train this model, -you can use the command: +We provide some examples about how to build custom projects based on OpenMMLAB codebases and MIM in [MIM-Example](https://github.com/open-mmlab/mim-example). In [mmcls_custom_backbone](https://github.com/open-mmlab/mim-example/tree/master/mmcls_custom_backbone), we define a custom backbone and a classification config file that uses the backbone. To train this model, you can use the command: ```python -# The working directory is `examples/custom_backbone` -PYTHONPATH=$PWD:$PYTHONPATH mim train mmcls custom_net_config.py --work-dir \ -tmp --gpus 1 +# The working directory is `mim-example/mmcls_custom_backbone` +PYTHONPATH=$PWD:$PYTHONPATH mim train mmcls custom_net_config.py --work-dir tmp --gpus 1 ```