2.2 KiB

Raw Blame History

Segmentation

Segmentation
- Train
- Test

For semantic segmentation task, we use MMSegmentation. First, make sure you have installed MIM, which is also a project of OpenMMLab.

pip install openmim

It is very easy to install the package.

Besides, please refer to MMSegmentation for installation and data preparation.

Train

After installation, you can run MMSeg with simple command.

# distributed version
bash tools/benchmarks/mmsegmentation/mim_dist_train.sh ${CONFIG} ${PRETRAIN} ${GPUS}

# slurm version
bash tools/benchmarks/mmsegmentation/mim_slurm_train.sh ${PARTITION} ${CONFIG} ${PRETRAIN}

Remarks:

CONFIG: Use config files under configs/benchmarks/mmsegmentation/. Since repositories of OpenMMLab have support referring config files across different repositories, we can easily leverage the configs from MMSegmentation like:

_base_ = 'mmseg::fcn/fcn_r50-d8_769x769_40k_cityscapes.py'

Writing your config files from scratch is also supported.

PRETRAIN: the pre-trained model file.
GPUS: The number of GPUs that you want to use to train. We adopt 4 GPUs for segmentation tasks by default.

Example:

bash ./tools/benchmarks/mmsegmentation/mim_dist_train.sh \
configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_512x512_20k_voc12aug.py \
work_dir/byol_resnet50_8xb32-accum16-coslr-200e_in1k_20220225-5c8b2c2e.pth 4

Test

After training, you can also run the command below to test your model.

# distributed version
bash tools/benchmarks/mmsegmentation/mim_dist_test.sh ${CONFIG} ${CHECKPOINT} ${GPUS}

# slurm version
bash tools/benchmarks/mmsegmentation/mim_slurm_test.sh ${PARTITION} ${CONFIG} ${CHECKPOINT}