mirror of
https://github.com/open-mmlab/mmsegmentation.git
synced 2025-06-03 22:03:48 +08:00
[Enhancement] Add Dev tools to boost develop (#798)
* Modify default work dir when training. * Refactor gather_models.py. * Add train and test matching list. * Regression benchmark list. * lower readme name to upper readme name. * Add url check tool and model inference test tool. * Modify tool name. * Support duplicate mode of log json url check. * Add regression benchmark evaluation automatic tool. * Add train script generator. * Only Support script running. * Add evaluation results gather. * Add exec Authority. * Automatically make checkpoint root folder. * Modify gather results save path. * Coarse-grained train results gather tool. * Complete benchmark train script. * Make some little modifications. * Fix checkpoint urls. * Fix unet checkpoint urls. * Fix fast scnn & fcn checkpoint url. * Fix fast scnn checkpoint urls. * Fix fast scnn url. * Add differential results calculation. * Add differential results of regression benchmark train results. * Add an extra argument to select model. * Update nonlocal_net & hrnet checkpoint url. * Fix checkpoint url of hrnet and Fix some tta evaluation results and modify gather models tool. * Modify fast scnn checkpoint url. * Resolve new comments. * Fix url check status code bug. * Resolve some comments. * Modify train scripts generator. * Modify work_dir of regression benchmark results. * model gather tool modification.
This commit is contained in:
sennnnn
GitHub
parent
4981ff68c2
commit
d35fbbdb47
133
.dev/batch_test_list.py
Normal file
133
.dev/batch_test_list.py
Normal file
@ -0,0 +1,133 @@
|
||||
# yapf: disable
|
||||
# Inference Speed is tested on NVIDIA V100
|
||||
hrnet = [
|
||||
dict(
|
||||
config='configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py',
|
||||
checkpoint='fcn_hr18s_512x512_160k_ade20k_20200614_214413-870f65ac.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=33.0),
|
||||
),
|
||||
dict(
|
||||
config='configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py',
|
||||
checkpoint='fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=76.31),
|
||||
),
|
||||
dict(
|
||||
config='configs/hrnet/fcn_hr48_512x512_160k_ade20k.py',
|
||||
checkpoint='fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth',
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=42.02),
|
||||
),
|
||||
dict(
|
||||
config='configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py',
|
||||
checkpoint='fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=80.65),
|
||||
),
|
||||
]
|
||||
pspnet = [
|
||||
dict(
|
||||
config='configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py',
|
||||
checkpoint='pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=78.55),
|
||||
),
|
||||
dict(
|
||||
config='configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py',
|
||||
checkpoint='pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=79.76),
|
||||
),
|
||||
dict(
|
||||
config='configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py',
|
||||
checkpoint='pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=44.39),
|
||||
),
|
||||
dict(
|
||||
config='configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py',
|
||||
checkpoint='pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=42.48),
|
||||
),
|
||||
]
|
||||
resnest = [
|
||||
dict(
|
||||
config='configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py',
|
||||
checkpoint='pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=45.44),
|
||||
),
|
||||
dict(
|
||||
config='configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py',
|
||||
checkpoint='pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=78.57),
|
||||
),
|
||||
]
|
||||
fastscnn = [
|
||||
dict(
|
||||
config='configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py',
|
||||
checkpoint='fast_scnn_8x4_160k_lr0.12_cityscapes-0cec9937.pth',
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=70.96),
|
||||
)
|
||||
]
|
||||
deeplabv3plus = [
|
||||
dict(
|
||||
config='configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py', # noqa
|
||||
checkpoint='deeplabv3plus_r101-d8_769x769_80k_cityscapes_20200607_000405-a7573d20.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=80.98),
|
||||
),
|
||||
dict(
|
||||
config='configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py', # noqa
|
||||
checkpoint='deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=80.97),
|
||||
),
|
||||
dict(
|
||||
config='configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py', # noqa
|
||||
checkpoint='deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=80.09),
|
||||
),
|
||||
dict(
|
||||
config='configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py', # noqa
|
||||
checkpoint='deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=79.83),
|
||||
),
|
||||
]
|
||||
vit = [
|
||||
dict(
|
||||
config='configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py',
|
||||
checkpoint='upernet_vit-b16_ln_mln_512x512_160k_ade20k-f444c077.pth',
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=47.73),
|
||||
),
|
||||
dict(
|
||||
config='configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py',
|
||||
checkpoint='upernet_deit-s16_ln_mln_512x512_160k_ade20k-c0cd652f.pth',
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=43.52),
|
||||
),
|
||||
]
|
||||
fp16 = [
|
||||
dict(
|
||||
config='configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py', # noqa
|
||||
checkpoint='deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes-cc58bc8d.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=80.46),
|
||||
)
|
||||
]
|
||||
swin = [
|
||||
dict(
|
||||
config='configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py', # noqa
|
||||
checkpoint='upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth', # noqa
|
||||
eval='mIoU',
|
||||
metric=dict(mIoU=44.41),
|
||||
)
|
||||
]
|
||||
# yapf: enable
|
||||
19
.dev/batch_train_list.txt
Normal file
19
.dev/batch_train_list.txt
Normal file
@ -0,0 +1,19 @@
|
||||
configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py
|
||||
configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py
|
||||
configs/hrnet/fcn_hr48_512x512_160k_ade20k.py
|
||||
configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py
|
||||
configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py
|
||||
configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py
|
||||
configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py
|
||||
configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py
|
||||
configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py
|
||||
configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py
|
||||
configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py
|
||||
configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py
|
||||
configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py
|
||||
configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py
|
||||
configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py
|
||||
configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py
|
||||
configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py
|
||||
configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py
|
||||
configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py
|
||||
41
.dev/benchmark_evaluation.sh
Executable file
41
.dev/benchmark_evaluation.sh
Executable file
@ -0,0 +1,41 @@
|
||||
PARTITION=$1
|
||||
CHECKPOINT_DIR=$2
|
||||
|
||||
echo 'configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION fcn_hr18s_512x512_160k_ade20k configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py $CHECKPOINT_DIR/fcn_hr18s_512x512_160k_ade20k_20200614_214413-870f65ac.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/fcn_hr18s_512x512_160k_ade20k --options dist_params.port=28171 &
|
||||
echo 'configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION fcn_hr18s_512x1024_160k_cityscapes configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py $CHECKPOINT_DIR/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/fcn_hr18s_512x1024_160k_cityscapes --options dist_params.port=28172 &
|
||||
echo 'configs/hrnet/fcn_hr48_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION fcn_hr48_512x512_160k_ade20k configs/hrnet/fcn_hr48_512x512_160k_ade20k.py $CHECKPOINT_DIR/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/fcn_hr48_512x512_160k_ade20k --options dist_params.port=28173 &
|
||||
echo 'configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION fcn_hr48_512x1024_160k_cityscapes configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py $CHECKPOINT_DIR/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/fcn_hr48_512x1024_160k_cityscapes --options dist_params.port=28174 &
|
||||
echo 'configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION pspnet_r50-d8_512x1024_80k_cityscapes configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py $CHECKPOINT_DIR/pspnet_r50-d8_512x1024_80k_cityscapes_20200606_112131-2376f12b.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/pspnet_r50-d8_512x1024_80k_cityscapes --options dist_params.port=28175 &
|
||||
echo 'configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION pspnet_r101-d8_512x1024_80k_cityscapes configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py $CHECKPOINT_DIR/pspnet_r101-d8_512x1024_80k_cityscapes_20200606_112211-e1e1100f.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/pspnet_r101-d8_512x1024_80k_cityscapes --options dist_params.port=28176 &
|
||||
echo 'configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION pspnet_r101-d8_512x512_160k_ade20k configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py $CHECKPOINT_DIR/pspnet_r101-d8_512x512_160k_ade20k_20200615_100650-967c316f.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/pspnet_r101-d8_512x512_160k_ade20k --options dist_params.port=28177 &
|
||||
echo 'configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION pspnet_r50-d8_512x512_160k_ade20k configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py $CHECKPOINT_DIR/pspnet_r50-d8_512x512_160k_ade20k_20200615_184358-1890b0bd.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/pspnet_r50-d8_512x512_160k_ade20k --options dist_params.port=28178 &
|
||||
echo 'configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION pspnet_s101-d8_512x512_160k_ade20k configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py $CHECKPOINT_DIR/pspnet_s101-d8_512x512_160k_ade20k_20200807_145416-a6daa92a.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/pspnet_s101-d8_512x512_160k_ade20k --options dist_params.port=28179 &
|
||||
echo 'configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION pspnet_s101-d8_512x1024_80k_cityscapes configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py $CHECKPOINT_DIR/pspnet_s101-d8_512x1024_80k_cityscapes_20200807_140631-c75f3b99.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/pspnet_s101-d8_512x1024_80k_cityscapes --options dist_params.port=28180 &
|
||||
echo 'configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION fast_scnn_lr0.12_8x4_160k_cityscapes configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py $CHECKPOINT_DIR/fast_scnn_8x4_160k_lr0.12_cityscapes-0cec9937.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/fast_scnn_lr0.12_8x4_160k_cityscapes --options dist_params.port=28181 &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION deeplabv3plus_r101-d8_769x769_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py $CHECKPOINT_DIR/deeplabv3plus_r101-d8_769x769_80k_cityscapes_20200607_000405-a7573d20.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/deeplabv3plus_r101-d8_769x769_80k_cityscapes --options dist_params.port=28182 &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION deeplabv3plus_r101-d8_512x1024_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py $CHECKPOINT_DIR/deeplabv3plus_r101-d8_512x1024_80k_cityscapes_20200606_114143-068fcfe9.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/deeplabv3plus_r101-d8_512x1024_80k_cityscapes --options dist_params.port=28183 &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION deeplabv3plus_r50-d8_512x1024_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py $CHECKPOINT_DIR/deeplabv3plus_r50-d8_512x1024_80k_cityscapes_20200606_114049-f9fb496d.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/deeplabv3plus_r50-d8_512x1024_80k_cityscapes --options dist_params.port=28184 &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION deeplabv3plus_r50-d8_769x769_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py $CHECKPOINT_DIR/deeplabv3plus_r50-d8_769x769_80k_cityscapes_20200606_210233-0e9dfdc4.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/deeplabv3plus_r50-d8_769x769_80k_cityscapes --options dist_params.port=28185 &
|
||||
echo 'configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION upernet_vit-b16_ln_mln_512x512_160k_ade20k configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py $CHECKPOINT_DIR/upernet_vit-b16_ln_mln_512x512_160k_ade20k-f444c077.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/upernet_vit-b16_ln_mln_512x512_160k_ade20k --options dist_params.port=28186 &
|
||||
echo 'configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION upernet_deit-s16_ln_mln_512x512_160k_ade20k configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py $CHECKPOINT_DIR/upernet_deit-s16_ln_mln_512x512_160k_ade20k-c0cd652f.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/upernet_deit-s16_ln_mln_512x512_160k_ade20k --options dist_params.port=28187 &
|
||||
echo 'configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py $CHECKPOINT_DIR/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes-cc58bc8d.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes --options dist_params.port=28188 &
|
||||
echo 'configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 tools/slurm_test.sh $PARTITION upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py $CHECKPOINT_DIR/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K_20210531_112542-e380ad3e.pth --eval mIoU --work-dir work_dirs/benchmark_evaluation/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K --options dist_params.port=28189 &
|
||||
149
.dev/benchmark_inference.py
Normal file
149
.dev/benchmark_inference.py
Normal file
@ -0,0 +1,149 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import hashlib
|
||||
import logging
|
||||
import os
|
||||
import os.path as osp
|
||||
import warnings
|
||||
from argparse import ArgumentParser
|
||||
|
||||
import requests
|
||||
from mmcv import Config
|
||||
|
||||
from mmseg.apis import inference_segmentor, init_segmentor, show_result_pyplot
|
||||
from mmseg.utils import get_root_logger
|
||||
|
||||
# ignore warnings when segmentors inference
|
||||
warnings.filterwarnings('ignore')
|
||||
|
||||
|
||||
def download_checkpoint(checkpoint_name, model_name, config_name, collect_dir):
|
||||
"""Download checkpoint and check if hash code is true."""
|
||||
url = f'https://download.openmmlab.com/mmsegmentation/v0.5/{model_name}/{config_name}/{checkpoint_name}' # noqa
|
||||
|
||||
r = requests.get(url)
|
||||
assert r.status_code != 403, f'{url} Access denied.'
|
||||
|
||||
with open(osp.join(collect_dir, checkpoint_name), 'wb') as code:
|
||||
code.write(r.content)
|
||||
|
||||
true_hash_code = osp.splitext(checkpoint_name)[0].split('-')[1]
|
||||
|
||||
# check hash code
|
||||
with open(osp.join(collect_dir, checkpoint_name), 'rb') as fp:
|
||||
sha256_cal = hashlib.sha256()
|
||||
sha256_cal.update(fp.read())
|
||||
cur_hash_code = sha256_cal.hexdigest()[:8]
|
||||
|
||||
assert true_hash_code == cur_hash_code, f'{url} download failed, '
|
||||
'incomplete downloaded file or url invalid.'
|
||||
|
||||
if cur_hash_code != true_hash_code:
|
||||
os.remove(osp.join(collect_dir, checkpoint_name))
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = ArgumentParser()
|
||||
parser.add_argument('config', help='test config file path')
|
||||
parser.add_argument('checkpoint_root', help='Checkpoint file root path')
|
||||
parser.add_argument(
|
||||
'-i', '--img', default='demo/demo.png', help='Image file')
|
||||
parser.add_argument('-a', '--aug', action='store_true', help='aug test')
|
||||
parser.add_argument('-m', '--model-name', help='model name to inference')
|
||||
parser.add_argument(
|
||||
'-s', '--show', action='store_true', help='show results')
|
||||
parser.add_argument(
|
||||
'-d', '--device', default='cuda:0', help='Device used for inference')
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def inference_model(config_name, checkpoint, args, logger=None):
|
||||
cfg = Config.fromfile(config_name)
|
||||
if args.aug:
|
||||
if 'flip' in cfg.data.test.pipeline[
|
||||
1] and 'img_scale' in cfg.data.test.pipeline[1]:
|
||||
cfg.data.test.pipeline[1].img_ratios = [
|
||||
0.5, 0.75, 1.0, 1.25, 1.5, 1.75
|
||||
]
|
||||
cfg.data.test.pipeline[1].flip = True
|
||||
else:
|
||||
if logger is not None:
|
||||
logger.error(f'{config_name}: unable to start aug test')
|
||||
else:
|
||||
print(f'{config_name}: unable to start aug test', flush=True)
|
||||
|
||||
model = init_segmentor(cfg, checkpoint, device=args.device)
|
||||
# test a single image
|
||||
result = inference_segmentor(model, args.img)
|
||||
|
||||
# show the results
|
||||
if args.show:
|
||||
show_result_pyplot(model, args.img, result)
|
||||
return result
|
||||
|
||||
|
||||
# Sample test whether the inference code is correct
|
||||
def main(args):
|
||||
config = Config.fromfile(args.config)
|
||||
|
||||
if not os.path.exists(args.checkpoint_root):
|
||||
os.makedirs(args.checkpoint_root, 0o775)
|
||||
|
||||
# test single model
|
||||
if args.model_name:
|
||||
if args.model_name in config:
|
||||
model_infos = config[args.model_name]
|
||||
if not isinstance(model_infos, list):
|
||||
model_infos = [model_infos]
|
||||
for model_info in model_infos:
|
||||
config_name = model_info['config'].strip()
|
||||
print(f'processing: {config_name}', flush=True)
|
||||
checkpoint = osp.join(args.checkpoint_root,
|
||||
model_info['checkpoint'].strip())
|
||||
try:
|
||||
# build the model from a config file and a checkpoint file
|
||||
inference_model(config_name, checkpoint, args)
|
||||
except Exception:
|
||||
print(f'{config_name} test failed!')
|
||||
continue
|
||||
return
|
||||
else:
|
||||
raise RuntimeError('model name input error.')
|
||||
|
||||
# test all model
|
||||
logger = get_root_logger(
|
||||
log_file='benchmark_inference_image.log', log_level=logging.ERROR)
|
||||
|
||||
for model_name in config:
|
||||
model_infos = config[model_name]
|
||||
|
||||
if not isinstance(model_infos, list):
|
||||
model_infos = [model_infos]
|
||||
for model_info in model_infos:
|
||||
print('processing: ', model_info['config'], flush=True)
|
||||
config_path = model_info['config'].strip()
|
||||
config_name = osp.splitext(osp.basename(config_path))[0]
|
||||
checkpoint_name = model_info['checkpoint'].strip()
|
||||
checkpoint = osp.join(args.checkpoint_root, checkpoint_name)
|
||||
|
||||
# ensure checkpoint exists
|
||||
try:
|
||||
if not osp.exists(checkpoint):
|
||||
download_checkpoint(checkpoint_name, model_name,
|
||||
config_name.rstrip('.py'),
|
||||
args.checkpoint_root)
|
||||
except Exception:
|
||||
logger.error(f'{checkpoint_name} download error')
|
||||
continue
|
||||
|
||||
# test model inference with checkpoint
|
||||
try:
|
||||
# build the model from a config file and a checkpoint file
|
||||
inference_model(config_path, checkpoint, args, logger)
|
||||
except Exception as e:
|
||||
logger.error(f'{config_path} " : {repr(e)}')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
args = parse_args()
|
||||
main(args)
|
||||
40
.dev/benchmark_train.sh
Executable file
40
.dev/benchmark_train.sh
Executable file
@ -0,0 +1,40 @@
|
||||
PARTITION=$1
|
||||
|
||||
echo 'configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION fcn_hr18s_512x512_160k_ade20k configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24727 --work-dir work_dirs/hrnet/fcn_hr18s_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION fcn_hr18s_512x1024_160k_cityscapes configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24728 --work-dir work_dirs/hrnet/fcn_hr18s_512x1024_160k_cityscapes >/dev/null &
|
||||
echo 'configs/hrnet/fcn_hr48_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION fcn_hr48_512x512_160k_ade20k configs/hrnet/fcn_hr48_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24729 --work-dir work_dirs/hrnet/fcn_hr48_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION fcn_hr48_512x1024_160k_cityscapes configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24730 --work-dir work_dirs/hrnet/fcn_hr48_512x1024_160k_cityscapes >/dev/null &
|
||||
echo 'configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION pspnet_r50-d8_512x1024_80k_cityscapes configs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24731 --work-dir work_dirs/pspnet/pspnet_r50-d8_512x1024_80k_cityscapes >/dev/null &
|
||||
echo 'configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION pspnet_r101-d8_512x1024_80k_cityscapes configs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24732 --work-dir work_dirs/pspnet/pspnet_r101-d8_512x1024_80k_cityscapes >/dev/null &
|
||||
echo 'configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION pspnet_r101-d8_512x512_160k_ade20k configs/pspnet/pspnet_r101-d8_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24733 --work-dir work_dirs/pspnet/pspnet_r101-d8_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION pspnet_r50-d8_512x512_160k_ade20k configs/pspnet/pspnet_r50-d8_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24734 --work-dir work_dirs/pspnet/pspnet_r50-d8_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION pspnet_s101-d8_512x512_160k_ade20k configs/resnest/pspnet_s101-d8_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24735 --work-dir work_dirs/resnest/pspnet_s101-d8_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION pspnet_s101-d8_512x1024_80k_cityscapes configs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24736 --work-dir work_dirs/resnest/pspnet_s101-d8_512x1024_80k_cityscapes >/dev/null &
|
||||
echo 'configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION fast_scnn_lr0.12_8x4_160k_cityscapes configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24737 --work-dir work_dirs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes >/dev/null &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION deeplabv3plus_r101-d8_769x769_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24738 --work-dir work_dirs/deeplabv3plus/deeplabv3plus_r101-d8_769x769_80k_cityscapes >/dev/null &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION deeplabv3plus_r101-d8_512x1024_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24739 --work-dir work_dirs/deeplabv3plus/deeplabv3plus_r101-d8_512x1024_80k_cityscapes >/dev/null &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION deeplabv3plus_r50-d8_512x1024_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24740 --work-dir work_dirs/deeplabv3plus/deeplabv3plus_r50-d8_512x1024_80k_cityscapes >/dev/null &
|
||||
echo 'configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION deeplabv3plus_r50-d8_769x769_80k_cityscapes configs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24741 --work-dir work_dirs/deeplabv3plus/deeplabv3plus_r50-d8_769x769_80k_cityscapes >/dev/null &
|
||||
echo 'configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py' &
|
||||
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION upernet_vit-b16_ln_mln_512x512_160k_ade20k configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24742 --work-dir work_dirs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py' &
|
||||
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION upernet_deit-s16_ln_mln_512x512_160k_ade20k configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24743 --work-dir work_dirs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k >/dev/null &
|
||||
echo 'configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py' &
|
||||
GPUS=4 GPUS_PER_NODE=4 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24744 --work-dir work_dirs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes >/dev/null &
|
||||
echo 'configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py' &
|
||||
GPUS=8 GPUS_PER_NODE=8 CPUS_PER_TASK=2 ./tools/slurm_train.sh $PARTITION upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py --options checkpoint_config.max_keep_ckpts=1 dist_params.port=24745 --work-dir work_dirs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K >/dev/null &
|
||||
101
.dev/check_urls.py
Normal file
101
.dev/check_urls.py
Normal file
@ -0,0 +1,101 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import logging
|
||||
import os
|
||||
from argparse import ArgumentParser
|
||||
|
||||
import requests
|
||||
import yaml as yml
|
||||
|
||||
from mmseg.utils import get_root_logger
|
||||
|
||||
|
||||
def check_url(url):
|
||||
"""Check url response status.
|
||||
|
||||
Args:
|
||||
url (str): url needed to check.
|
||||
|
||||
Returns:
|
||||
int, bool: status code and check flag.
|
||||
"""
|
||||
flag = True
|
||||
r = requests.head(url)
|
||||
status_code = r.status_code
|
||||
if status_code == 403 or status_code == 404:
|
||||
flag = False
|
||||
|
||||
return status_code, flag
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = ArgumentParser('url valid check.')
|
||||
parser.add_argument(
|
||||
'-m',
|
||||
'--model-name',
|
||||
type=str,
|
||||
help='Select the model needed to check')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
model_name = args.model_name
|
||||
|
||||
# yml path generate.
|
||||
# If model_name is not set, script will check all of the models.
|
||||
if model_name is not None:
|
||||
yml_list = [(model_name, f'configs/{model_name}/{model_name}.yml')]
|
||||
else:
|
||||
# check all
|
||||
yml_list = [(x, f'configs/{x}/{x}.yml') for x in os.listdir('configs/')
|
||||
if x != '_base_']
|
||||
|
||||
logger = get_root_logger(log_file='url_check.log', log_level=logging.ERROR)
|
||||
|
||||
for model_name, yml_path in yml_list:
|
||||
# Default yaml loader unsafe.
|
||||
model_infos = yml.load(
|
||||
open(yml_path, 'r'), Loader=yml.CLoader)['Models']
|
||||
for model_info in model_infos:
|
||||
config_name = model_info['Name']
|
||||
checkpoint_url = model_info['Weights']
|
||||
# checkpoint url check
|
||||
status_code, flag = check_url(checkpoint_url)
|
||||
if flag:
|
||||
logger.info(f'checkpoint | {config_name} | {checkpoint_url} | '
|
||||
f'{status_code} valid')
|
||||
else:
|
||||
logger.error(
|
||||
f'checkpoint | {config_name} | {checkpoint_url} | '
|
||||
f'{status_code} | error')
|
||||
# log_json check
|
||||
checkpoint_name = checkpoint_url.split('/')[-1]
|
||||
model_time = '-'.join(checkpoint_name.split('-')[:-1]).replace(
|
||||
f'{config_name}_', '')
|
||||
# two style of log_json name
|
||||
# use '_' to link model_time (will be deprecated)
|
||||
log_json_url_1 = f'https://download.openmmlab.com/mmsegmentation/v0.5/{model_name}/{config_name}/{config_name}_{model_time}.log.json' # noqa
|
||||
status_code_1, flag_1 = check_url(log_json_url_1)
|
||||
# use '-' to link model_time
|
||||
log_json_url_2 = f'https://download.openmmlab.com/mmsegmentation/v0.5/{model_name}/{config_name}/{config_name}-{model_time}.log.json' # noqa
|
||||
status_code_2, flag_2 = check_url(log_json_url_2)
|
||||
if flag_1 or flag_2:
|
||||
if flag_1:
|
||||
logger.info(
|
||||
f'log.json | {config_name} | {log_json_url_1} | '
|
||||
f'{status_code_1} | valid')
|
||||
else:
|
||||
logger.info(
|
||||
f'log.json | {config_name} | {log_json_url_2} | '
|
||||
f'{status_code_2} | valid')
|
||||
else:
|
||||
logger.error(
|
||||
f'log.json | {config_name} | {log_json_url_1} & '
|
||||
f'{log_json_url_2} | {status_code_1} & {status_code_2} | '
|
||||
'error')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
91
.dev/gather_benchmark_evaluation_results.py
Normal file
91
.dev/gather_benchmark_evaluation_results.py
Normal file
@ -0,0 +1,91 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import argparse
|
||||
import glob
|
||||
import os.path as osp
|
||||
|
||||
import mmcv
|
||||
from mmcv import Config
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Gather benchmarked model evaluation results')
|
||||
parser.add_argument('config', help='test config file path')
|
||||
parser.add_argument(
|
||||
'root',
|
||||
type=str,
|
||||
help='root path of benchmarked models to be gathered')
|
||||
parser.add_argument(
|
||||
'--out',
|
||||
type=str,
|
||||
default='benchmark_evaluation_info.json',
|
||||
help='output path of gathered metrics and compared '
|
||||
'results to be stored')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
args = parse_args()
|
||||
|
||||
root_path = args.root
|
||||
metrics_out = args.out
|
||||
result_dict = {}
|
||||
|
||||
cfg = Config.fromfile(args.config)
|
||||
|
||||
for model_key in cfg:
|
||||
model_infos = cfg[model_key]
|
||||
if not isinstance(model_infos, list):
|
||||
model_infos = [model_infos]
|
||||
for model_info in model_infos:
|
||||
previous_metrics = model_info['metric']
|
||||
config = model_info['config'].strip()
|
||||
fname, _ = osp.splitext(osp.basename(config))
|
||||
|
||||
# Load benchmark evaluation json
|
||||
metric_json_dir = osp.join(root_path, fname)
|
||||
if not osp.exists(metric_json_dir):
|
||||
print(f'{metric_json_dir} not existed.')
|
||||
continue
|
||||
|
||||
json_list = glob.glob(osp.join(metric_json_dir, '*.json'))
|
||||
if len(json_list) == 0:
|
||||
print(f'There is no eval json in {metric_json_dir}.')
|
||||
continue
|
||||
|
||||
log_json_path = list(sorted(json_list))[-1]
|
||||
metric = mmcv.load(log_json_path)
|
||||
if config not in metric.get('config', {}):
|
||||
print(f'{config} not included in {log_json_path}')
|
||||
continue
|
||||
|
||||
# Compare between new benchmark results and previous metrics
|
||||
differential_results = dict()
|
||||
new_metrics = dict()
|
||||
for record_metric_key in previous_metrics:
|
||||
if record_metric_key not in metric['metric']:
|
||||
raise KeyError('record_metric_key not exist, please '
|
||||
'check your config')
|
||||
old_metric = previous_metrics[record_metric_key]
|
||||
new_metric = round(metric['metric'][record_metric_key] * 100,
|
||||
2)
|
||||
|
||||
differential = new_metric - old_metric
|
||||
flag = '+' if differential > 0 else '-'
|
||||
differential_results[
|
||||
record_metric_key] = f'{flag}{abs(differential):.2f}'
|
||||
new_metrics[record_metric_key] = new_metric
|
||||
|
||||
result_dict[config] = dict(
|
||||
differential=differential_results,
|
||||
previous=previous_metrics,
|
||||
new=new_metrics)
|
||||
|
||||
if metrics_out:
|
||||
mmcv.dump(result_dict, metrics_out, indent=4)
|
||||
print('===================================')
|
||||
for config_name, metrics in result_dict.items():
|
||||
print(config_name, metrics)
|
||||
print('===================================')
|
||||
100
.dev/gather_benchmark_train_results.py
Normal file
100
.dev/gather_benchmark_train_results.py
Normal file
@ -0,0 +1,100 @@
|
||||
import argparse
|
||||
import glob
|
||||
import os.path as osp
|
||||
|
||||
import mmcv
|
||||
from gather_models import get_final_results
|
||||
from mmcv import Config
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Gather benchmarked models train results')
|
||||
parser.add_argument('config', help='test config file path')
|
||||
parser.add_argument(
|
||||
'root',
|
||||
type=str,
|
||||
help='root path of benchmarked models to be gathered')
|
||||
parser.add_argument(
|
||||
'--out',
|
||||
type=str,
|
||||
default='benchmark_train_info.json',
|
||||
help='output path of gathered metrics to be stored')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
args = parse_args()
|
||||
|
||||
root_path = args.root
|
||||
metrics_out = args.out
|
||||
|
||||
evaluation_cfg = Config.fromfile(args.config)
|
||||
|
||||
result_dict = {}
|
||||
for model_key in evaluation_cfg:
|
||||
model_infos = evaluation_cfg[model_key]
|
||||
if not isinstance(model_infos, list):
|
||||
model_infos = [model_infos]
|
||||
for model_info in model_infos:
|
||||
config = model_info['config']
|
||||
|
||||
# benchmark train dir
|
||||
model_name = osp.split(osp.dirname(config))[1]
|
||||
config_name = osp.splitext(osp.basename(config))[0]
|
||||
exp_dir = osp.join(root_path, model_name, config_name)
|
||||
if not osp.exists(exp_dir):
|
||||
print(f'{config} hasn\'t {exp_dir}')
|
||||
continue
|
||||
|
||||
# parse config
|
||||
cfg = mmcv.Config.fromfile(config)
|
||||
total_iters = cfg.runner.max_iters
|
||||
exp_metric = cfg.evaluation.metric
|
||||
if not isinstance(exp_metric, list):
|
||||
exp_metrics = [exp_metric]
|
||||
|
||||
# determine whether total_iters ckpt exists
|
||||
ckpt_path = f'iter_{total_iters}.pth'
|
||||
if not osp.exists(osp.join(exp_dir, ckpt_path)):
|
||||
print(f'{config} hasn\'t {ckpt_path}')
|
||||
continue
|
||||
|
||||
# only the last log json counts
|
||||
log_json_path = list(
|
||||
sorted(glob.glob(osp.join(exp_dir, '*.log.json'))))[-1]
|
||||
|
||||
# extract metric value
|
||||
model_performance = get_final_results(log_json_path, total_iters)
|
||||
if model_performance is None:
|
||||
print(f'log file error: {log_json_path}')
|
||||
continue
|
||||
|
||||
differential_results = dict()
|
||||
old_results = dict()
|
||||
new_results = dict()
|
||||
for metric_key in model_performance:
|
||||
if metric_key in ['mIoU']:
|
||||
metric = round(model_performance[metric_key] * 100, 2)
|
||||
old_metric = model_info['metric'][metric_key]
|
||||
old_results[metric_key] = old_metric
|
||||
new_results[metric_key] = metric
|
||||
differential = metric - old_metric
|
||||
flag = '+' if differential > 0 else '-'
|
||||
differential_results[
|
||||
metric_key] = f'{flag}{abs(differential):.2f}'
|
||||
result_dict[config] = dict(
|
||||
differential_results=differential_results,
|
||||
old_results=old_results,
|
||||
new_results=new_results,
|
||||
)
|
||||
|
||||
# 4 save or print results
|
||||
if metrics_out:
|
||||
mmcv.dump(result_dict, metrics_out, indent=4)
|
||||
print('===================================')
|
||||
for config_name, metrics in result_dict.items():
|
||||
print(config_name, metrics)
|
||||
print('===================================')
|
||||
@ -1,11 +1,11 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import argparse
|
||||
import glob
|
||||
import hashlib
|
||||
import json
|
||||
import os
|
||||
import os.path as osp
|
||||
import shutil
|
||||
import subprocess
|
||||
|
||||
import mmcv
|
||||
import torch
|
||||
@ -14,6 +14,14 @@ import torch
|
||||
RESULTS_LUT = ['mIoU', 'mAcc', 'aAcc']
|
||||
|
||||
|
||||
def calculate_file_sha256(file_path):
|
||||
"""calculate file sha256 hash code."""
|
||||
with open(file_path, 'rb') as fp:
|
||||
sha256_cal = hashlib.sha256()
|
||||
sha256_cal.update(fp.read())
|
||||
return sha256_cal.hexdigest()
|
||||
|
||||
|
||||
def process_checkpoint(in_file, out_file):
|
||||
checkpoint = torch.load(in_file, map_location='cpu')
|
||||
# remove optimizer for smaller file size
|
||||
@ -22,10 +30,17 @@ def process_checkpoint(in_file, out_file):
|
||||
# if it is necessary to remove some sensitive data in checkpoint['meta'],
|
||||
# add the code here.
|
||||
torch.save(checkpoint, out_file)
|
||||
sha = subprocess.check_output(['sha256sum', out_file]).decode()
|
||||
# The hash code calculation and rename command differ on different system
|
||||
# platform.
|
||||
sha = calculate_file_sha256(out_file)
|
||||
final_file = out_file.rstrip('.pth') + '-{}.pth'.format(sha[:8])
|
||||
subprocess.Popen(['mv', out_file, final_file])
|
||||
return final_file
|
||||
os.rename(out_file, final_file)
|
||||
|
||||
# Remove prefix and suffix
|
||||
final_file_name = osp.split(final_file)[1]
|
||||
final_file_name = osp.splitext(final_file_name)[0]
|
||||
|
||||
return final_file_name
|
||||
|
||||
|
||||
def get_final_iter(config):
|
||||
@ -36,40 +51,43 @@ def get_final_iter(config):
|
||||
|
||||
def get_final_results(log_json_path, iter_num):
|
||||
result_dict = dict()
|
||||
last_iter = 0
|
||||
with open(log_json_path, 'r') as f:
|
||||
for line in f.readlines():
|
||||
log_line = json.loads(line)
|
||||
if 'mode' not in log_line.keys():
|
||||
continue
|
||||
|
||||
if log_line['mode'] == 'train' and log_line['iter'] == iter_num:
|
||||
result_dict['memory'] = log_line['memory']
|
||||
|
||||
if log_line['iter'] == iter_num:
|
||||
# When evaluation, the 'iter' of new log json is the evaluation
|
||||
# steps on single gpu.
|
||||
flag1 = ('aAcc' in log_line) or (log_line['mode'] == 'val')
|
||||
flag2 = (last_iter == iter_num - 50) or (last_iter == iter_num)
|
||||
if flag1 and flag2:
|
||||
result_dict.update({
|
||||
key: log_line[key]
|
||||
for key in RESULTS_LUT if key in log_line
|
||||
})
|
||||
return result_dict
|
||||
|
||||
last_iter = log_line['iter']
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(description='Gather benchmarked models')
|
||||
parser.add_argument(
|
||||
'root',
|
||||
type=str,
|
||||
help='root path of benchmarked models to be gathered')
|
||||
'-c', '--config-name', type=str, help='Process the selected config.')
|
||||
parser.add_argument(
|
||||
'config',
|
||||
'-w',
|
||||
'--work-dir',
|
||||
default='work_dirs/',
|
||||
type=str,
|
||||
help='root path of benchmarked configs to be gathered')
|
||||
help='Ckpt storage root folder of benchmarked models to be gathered.')
|
||||
parser.add_argument(
|
||||
'out_dir',
|
||||
'-c',
|
||||
'--collect-dir',
|
||||
default='work_dirs/gather',
|
||||
type=str,
|
||||
help='output path of gathered models to be stored')
|
||||
parser.add_argument('out_file', type=str, help='the output json file name')
|
||||
parser.add_argument(
|
||||
'--filter', type=str, nargs='+', default=[], help='config filter')
|
||||
help='Ckpt collect root folder of gathered models.')
|
||||
parser.add_argument(
|
||||
'--all', action='store_true', help='whether include .py and .log')
|
||||
|
||||
@ -79,34 +97,30 @@ def parse_args():
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
models_root = args.root
|
||||
models_out = args.out_dir
|
||||
config_name = args.config
|
||||
mmcv.mkdir_or_exist(models_out)
|
||||
work_dir = args.work_dir
|
||||
collect_dir = args.collect_dir
|
||||
selected_config_name = args.config_name
|
||||
mmcv.mkdir_or_exist(collect_dir)
|
||||
|
||||
# find all models in the root directory to be gathered
|
||||
raw_configs = list(mmcv.scandir(config_name, '.py', recursive=True))
|
||||
raw_configs = list(mmcv.scandir('./configs', '.py', recursive=True))
|
||||
|
||||
# filter configs that is not trained in the experiments dir
|
||||
used_configs = []
|
||||
for raw_config in raw_configs:
|
||||
work_dir = osp.splitext(osp.basename(raw_config))[0]
|
||||
if osp.exists(osp.join(models_root, work_dir)):
|
||||
used_configs.append((work_dir, raw_config))
|
||||
config_name = osp.splitext(osp.basename(raw_config))[0]
|
||||
if osp.exists(osp.join(work_dir, config_name)):
|
||||
if (selected_config_name is None
|
||||
or selected_config_name == config_name):
|
||||
used_configs.append(raw_config)
|
||||
print(f'Find {len(used_configs)} models to be gathered')
|
||||
|
||||
# find final_ckpt and log file for trained each config
|
||||
# and parse the best performance
|
||||
model_infos = []
|
||||
for used_config, raw_config in used_configs:
|
||||
bypass = True
|
||||
for p in args.filter:
|
||||
if p in used_config:
|
||||
bypass = False
|
||||
break
|
||||
if bypass:
|
||||
continue
|
||||
exp_dir = osp.join(models_root, used_config)
|
||||
for used_config in used_configs:
|
||||
config_name = osp.splitext(osp.basename(used_config))[0]
|
||||
exp_dir = osp.join(work_dir, config_name)
|
||||
# check whether the exps is finished
|
||||
final_iter = get_final_iter(used_config)
|
||||
final_model = 'iter_{}.pth'.format(final_iter)
|
||||
@ -134,8 +148,7 @@ def main():
|
||||
model_time = osp.split(log_json_path)[-1].split('.')[0]
|
||||
model_infos.append(
|
||||
dict(
|
||||
config=used_config,
|
||||
raw_config=raw_config,
|
||||
config_name=config_name,
|
||||
results=model_performance,
|
||||
iters=final_iter,
|
||||
model_time=model_time,
|
||||
@ -144,13 +157,12 @@ def main():
|
||||
# publish model for each checkpoint
|
||||
publish_model_infos = []
|
||||
for model in model_infos:
|
||||
model_publish_dir = osp.join(models_out,
|
||||
model['raw_config'].rstrip('.py'))
|
||||
model_name = osp.split(model['config'])[-1].split('.')[0]
|
||||
config_name = model['config_name']
|
||||
model_publish_dir = osp.join(collect_dir, config_name)
|
||||
|
||||
publish_model_path = osp.join(model_publish_dir,
|
||||
model_name + '_' + model['model_time'])
|
||||
trained_model_path = osp.join(models_root, model['config'],
|
||||
config_name + '_' + model['model_time'])
|
||||
trained_model_path = osp.join(work_dir, config_name,
|
||||
'iter_{}.pth'.format(model['iters']))
|
||||
if osp.exists(model_publish_dir):
|
||||
for file in os.listdir(model_publish_dir):
|
||||
@ -170,28 +182,29 @@ def main():
|
||||
publish_model_path)
|
||||
model['model_path'] = final_model_path
|
||||
|
||||
new_json_path = f'{model_name}-{model["log_json_path"]}'
|
||||
new_json_path = f'{config_name}_{model["log_json_path"]}'
|
||||
# copy log
|
||||
shutil.copy(
|
||||
osp.join(models_root, model['config'], model['log_json_path']),
|
||||
osp.join(work_dir, config_name, model['log_json_path']),
|
||||
osp.join(model_publish_dir, new_json_path))
|
||||
|
||||
if args.all:
|
||||
new_txt_path = new_json_path.rstrip('.json')
|
||||
shutil.copy(
|
||||
osp.join(models_root, model['config'],
|
||||
osp.join(work_dir, config_name,
|
||||
model['log_json_path'].rstrip('.json')),
|
||||
osp.join(model_publish_dir, new_txt_path))
|
||||
|
||||
if args.all:
|
||||
# copy config to guarantee reproducibility
|
||||
raw_config = osp.join(config_name, model['raw_config'])
|
||||
raw_config = osp.join('./configs', f'{config_name}.py')
|
||||
mmcv.Config.fromfile(raw_config).dump(
|
||||
osp.join(model_publish_dir, osp.basename(raw_config)))
|
||||
|
||||
publish_model_infos.append(model)
|
||||
|
||||
models = dict(models=publish_model_infos)
|
||||
mmcv.dump(models, osp.join(models_out, args.out_file))
|
||||
mmcv.dump(models, osp.join(collect_dir, 'model_infos.json'), indent=4)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
114
.dev/generate_benchmark_evaluation_script.py
Normal file
114
.dev/generate_benchmark_evaluation_script.py
Normal file
@ -0,0 +1,114 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import argparse
|
||||
import os.path as osp
|
||||
|
||||
from mmcv import Config
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Convert benchmark test model list to script')
|
||||
parser.add_argument('config', help='test config file path')
|
||||
parser.add_argument('--port', type=int, default=28171, help='dist port')
|
||||
parser.add_argument(
|
||||
'--work-dir',
|
||||
default='work_dirs/benchmark_evaluation',
|
||||
help='the dir to save metric')
|
||||
parser.add_argument(
|
||||
'--out',
|
||||
type=str,
|
||||
default='.dev/benchmark_evaluation.sh',
|
||||
help='path to save model benchmark script')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def process_model_info(model_info, work_dir):
|
||||
config = model_info['config'].strip()
|
||||
fname, _ = osp.splitext(osp.basename(config))
|
||||
job_name = fname
|
||||
checkpoint = model_info['checkpoint'].strip()
|
||||
work_dir = osp.join(work_dir, fname)
|
||||
if not isinstance(model_info['eval'], list):
|
||||
evals = [model_info['eval']]
|
||||
else:
|
||||
evals = model_info['eval']
|
||||
eval = ' '.join(evals)
|
||||
return dict(
|
||||
config=config,
|
||||
job_name=job_name,
|
||||
checkpoint=checkpoint,
|
||||
work_dir=work_dir,
|
||||
eval=eval)
|
||||
|
||||
|
||||
def create_test_bash_info(commands, model_test_dict, port, script_name,
|
||||
partition):
|
||||
config = model_test_dict['config']
|
||||
job_name = model_test_dict['job_name']
|
||||
checkpoint = model_test_dict['checkpoint']
|
||||
work_dir = model_test_dict['work_dir']
|
||||
eval = model_test_dict['eval']
|
||||
|
||||
echo_info = f'\necho \'{config}\' &'
|
||||
commands.append(echo_info)
|
||||
commands.append('\n')
|
||||
|
||||
command_info = f'GPUS=4 GPUS_PER_NODE=4 ' \
|
||||
f'CPUS_PER_TASK=2 {script_name} '
|
||||
|
||||
command_info += f'{partition} '
|
||||
command_info += f'{job_name} '
|
||||
command_info += f'{config} '
|
||||
command_info += f'$CHECKPOINT_DIR/{checkpoint} '
|
||||
|
||||
command_info += f'--eval {eval} '
|
||||
command_info += f'--work-dir {work_dir} '
|
||||
command_info += f'--options dist_params.port={port} '
|
||||
command_info += '&'
|
||||
|
||||
commands.append(command_info)
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
if args.out:
|
||||
out_suffix = args.out.split('.')[-1]
|
||||
assert args.out.endswith('.sh'), \
|
||||
f'Expected out file path suffix is .sh, but get .{out_suffix}'
|
||||
|
||||
commands = []
|
||||
partition_name = 'PARTITION=$1'
|
||||
commands.append(partition_name)
|
||||
commands.append('\n')
|
||||
|
||||
checkpoint_root = 'CHECKPOINT_DIR=$2'
|
||||
commands.append(checkpoint_root)
|
||||
commands.append('\n')
|
||||
|
||||
script_name = osp.join('tools', 'slurm_test.sh')
|
||||
port = args.port
|
||||
work_dir = args.work_dir
|
||||
|
||||
cfg = Config.fromfile(args.config)
|
||||
|
||||
for model_key in cfg:
|
||||
model_infos = cfg[model_key]
|
||||
if not isinstance(model_infos, list):
|
||||
model_infos = [model_infos]
|
||||
for model_info in model_infos:
|
||||
print('processing: ', model_info['config'])
|
||||
model_test_dict = process_model_info(model_info, work_dir)
|
||||
create_test_bash_info(commands, model_test_dict, port, script_name,
|
||||
'$PARTITION')
|
||||
port += 1
|
||||
|
||||
command_str = ''.join(commands)
|
||||
if args.out:
|
||||
with open(args.out, 'w') as f:
|
||||
f.write(command_str + '\n')
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
91
.dev/generate_benchmark_train_script.py
Normal file
91
.dev/generate_benchmark_train_script.py
Normal file
@ -0,0 +1,91 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import argparse
|
||||
import os.path as osp
|
||||
|
||||
# Default using 4 gpu when training
|
||||
config_8gpu_list = [
|
||||
'configs/swin/upernet_swin_tiny_patch4_window7_512x512_160k_ade20k_pretrain_224x224_1K.py', # noqa
|
||||
'configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py',
|
||||
'configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py',
|
||||
]
|
||||
|
||||
|
||||
def parse_args():
|
||||
parser = argparse.ArgumentParser(
|
||||
description='Convert benchmark model json to script')
|
||||
parser.add_argument(
|
||||
'txt_path', type=str, help='txt path output by benchmark_filter')
|
||||
parser.add_argument('--port', type=int, default=24727, help='dist port')
|
||||
parser.add_argument(
|
||||
'--out',
|
||||
type=str,
|
||||
default='.dev/benchmark_train.sh',
|
||||
help='path to save model benchmark script')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def create_train_bash_info(commands, config, script_name, partition, port):
|
||||
cfg = config.strip()
|
||||
|
||||
# print cfg name
|
||||
echo_info = f'echo \'{cfg}\' &'
|
||||
commands.append(echo_info)
|
||||
commands.append('\n')
|
||||
|
||||
_, model_name = osp.split(osp.dirname(cfg))
|
||||
config_name, _ = osp.splitext(osp.basename(cfg))
|
||||
# default setting
|
||||
if cfg in config_8gpu_list:
|
||||
command_info = f'GPUS=8 GPUS_PER_NODE=8 ' \
|
||||
f'CPUS_PER_TASK=2 {script_name} '
|
||||
else:
|
||||
command_info = f'GPUS=4 GPUS_PER_NODE=4 ' \
|
||||
f'CPUS_PER_TASK=2 {script_name} '
|
||||
command_info += f'{partition} '
|
||||
command_info += f'{config_name} '
|
||||
command_info += f'{cfg} '
|
||||
command_info += f'--options ' \
|
||||
f'checkpoint_config.max_keep_ckpts=1 ' \
|
||||
f'dist_params.port={port} '
|
||||
command_info += f'--work-dir work_dirs/{model_name}/{config_name} '
|
||||
# Let the script shut up
|
||||
command_info += '>/dev/null &'
|
||||
|
||||
commands.append(command_info)
|
||||
commands.append('\n')
|
||||
|
||||
|
||||
def main():
|
||||
args = parse_args()
|
||||
if args.out:
|
||||
out_suffix = args.out.split('.')[-1]
|
||||
assert args.out.endswith('.sh'), \
|
||||
f'Expected out file path suffix is .sh, but get .{out_suffix}'
|
||||
|
||||
root_name = './tools'
|
||||
script_name = osp.join(root_name, 'slurm_train.sh')
|
||||
port = args.port
|
||||
partition_name = 'PARTITION=$1'
|
||||
|
||||
commands = []
|
||||
commands.append(partition_name)
|
||||
commands.append('\n')
|
||||
commands.append('\n')
|
||||
|
||||
with open(args.txt_path, 'r') as f:
|
||||
model_cfgs = f.readlines()
|
||||
for i, cfg in enumerate(model_cfgs):
|
||||
create_train_bash_info(commands, cfg, script_name, '$PARTITION',
|
||||
port)
|
||||
port += 1
|
||||
|
||||
command_str = ''.join(commands)
|
||||
if args.out:
|
||||
with open(args.out, 'w') as f:
|
||||
f.write(command_str)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
@ -7,6 +7,7 @@ repos:
|
||||
rev: v2.2.0
|
||||
hooks:
|
||||
- id: seed-isort-config
|
||||
args: ["--exclude", ".dev"]
|
||||
- repo: https://github.com/timothycrosley/isort
|
||||
rev: 4.3.21
|
||||
hooks:
|
||||
|
||||
@ -19,4 +19,4 @@
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| --------- | --------- | --------- | ------: | -------- | -------------- | ----: | ------------- | --------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Fast-SCNN | Fast-SCNN | 512x1024 | 160000 | 3.3 | 56.45 | 70.96 | 72.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_8x4_160k_lr0.12_cityscapes-0cec9937.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_8x4_160k_lr0.12_cityscapes-20210630_164853.log.json) |
|
||||
| Fast-SCNN | Fast-SCNN | 512x1024 | 160000 | 3.3 | 56.45 | 70.96 | 72.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fastscnn/fast_scnn_lr0.12_8x4_160k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853.log.json) |
|
||||
|
||||
@ -25,4 +25,4 @@ Models:
|
||||
mIoU: 70.96
|
||||
mIoU(ms+flip): 72.65
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_8x4_160k_lr0.12_cityscapes-0cec9937.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fast_scnn/fast_scnn_lr0.12_8x4_160k_cityscapes/fast_scnn_lr0.12_8x4_160k_cityscapes_20210630_164853-0cec9937.pth
|
||||
|
||||
@ -39,18 +39,18 @@
|
||||
| FCN | R-18b-D8 | 769x769 | 80000 | 1.7 | 6.70 | 69.66 | 72.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r18b-d8_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes_20201226_004430-32d504e5.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r18b-d8_769x769_80k_cityscapes/fcn_r18b-d8_769x769_80k_cityscapes-20201226_004430.log.json) |
|
||||
| FCN | R-50b-D8 | 769x769 | 80000 | 6.3 | 1.82 | 73.83 | 76.60 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r50b-d8_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes_20201225_094223-94552d38.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r50b-d8_769x769_80k_cityscapes/fcn_r50b-d8_769x769_80k_cityscapes-20201225_094223.log.json) |
|
||||
| FCN | R-101b-D8 | 769x769 | 80000 | 10.3 | 1.15 | 77.02 | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r101b-d8_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes_20201226_170012-82be37e2.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101b-d8_769x769_80k_cityscapes/fcn_r101b-d8_769x769_80k_cityscapes-20201226_170012.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 512x1024 | 40000 | 3.4 | 10.22 | 77.06 | 78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-98d5d1bc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 512x1024 | 80000 | - | 10.35 | 77.27 | 78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-98d5d1bc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 769x769 | 40000 | 3.7 | 4.17 | 76.82 | 78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-1aab18ed.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 769x769 | 80000 | - | 4.15 | 77.04 | 78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-109d88eb.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 512x1024 | 40000 | 4.5 | 8.04 | 77.36 | 79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-9cf2b450.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 512x1024 | 80000 | - | 8.26 | 78.46 | 80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-cb336445.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 769x769 | 40000 | 5.0 | 3.12 | 77.28 | 78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-60b114e9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 769x769 | 80000 | - | 3.21 | 78.06 | 79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-e33adc4f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json) |
|
||||
| FCN-D6 | R-50b-D16 | 512x1024 | 80000 | 3.2 | 10.16 | 76.99 | 79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-6a0b62e9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json) |
|
||||
| FCN-D6 | R-50b-D16 | 769x769 | 80000 | 3.6 | 4.17 | 76.86 | 78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-d665f231.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json) |
|
||||
| FCN-D6 | R-101b-D16 | 512x1024 | 80000 | 4.3 | 8.46 | 77.72 | 79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-3f2eb5b4.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
|
||||
| FCN-D6 | R-101b-D16 | 769x769 | 80000 | 4.8 | 3.32 | 77.34 | 78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-c4d8bfbc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 512x1024 | 40000 | 3.4 | 10.22 | 77.06 | 78.85 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-20210305_130133.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 512x1024 | 80000 | - | 10.35 | 77.27 | 78.88 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes-20210306_115604.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 769x769 | 40000 | 3.7 | 4.17 | 76.82 | 78.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-20210305_185744.log.json) |
|
||||
| FCN-D6 | R-50-D16 | 769x769 | 80000 | - | 4.15 | 77.04 | 78.40 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-20210305_200413.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 512x1024 | 40000 | 4.5 | 8.04 | 77.36 | 79.18 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-20210305_130337.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 512x1024 | 80000 | - | 8.26 | 78.46 | 80.42 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-20210308_102747.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 769x769 | 40000 | 5.0 | 3.12 | 77.28 | 78.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-20210308_102453.log.json) |
|
||||
| FCN-D6 | R-101-D16 | 769x769 | 80000 | - | 3.21 | 78.06 | 79.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-20210306_120016.log.json) |
|
||||
| FCN-D6 | R-50b-D16 | 512x1024 | 80000 | 3.2 | 10.16 | 76.99 | 79.03 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-20210311_125550.log.json) |
|
||||
| FCN-D6 | R-50b-D16 | 769x769 | 80000 | 3.6 | 4.17 | 76.86 | 78.52 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-20210311_131012.log.json) |
|
||||
| FCN-D6 | R-101b-D16 | 512x1024 | 80000 | 4.3 | 8.46 | 77.72 | 79.53 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-20210311_144305.log.json) |
|
||||
| FCN-D6 | R-101b-D16 | 769x769 | 80000 | 4.8 | 3.32 | 77.34 | 78.91 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-20210311_154527.log.json) |
|
||||
|
||||
### ADE20K
|
||||
|
||||
@ -74,8 +74,8 @@
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| FCN | R-101-D8 | 480x480 | 40000 | - | 9.93 | 44.43 | 45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r101-d8_480x480_40k_pascal_context.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757-b5e97937.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757.log.json) |
|
||||
| FCN | R-101-D8 | 480x480 | 80000 | - | - | 44.13 | 45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r101-d8_480x480_80k_pascal_context.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310-4711813f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310.log.json) |
|
||||
| FCN | R-101-D8 | 480x480 | 40000 | - | 9.93 | 44.43 | 45.63 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r101-d8_480x480_40k_pascal_context.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757.log.json) |
|
||||
| FCN | R-101-D8 | 480x480 | 80000 | - | - | 44.13 | 45.26 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fcn/fcn_r101-d8_480x480_80k_pascal_context.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310.log.json) |
|
||||
|
||||
### Pascal Context 59
|
||||
|
||||
|
||||
@ -349,7 +349,7 @@ Models:
|
||||
mIoU: 77.06
|
||||
mIoU(ms+flip): 78.85
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-98d5d1bc.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_40k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes_20210305_130133-98d5d1bc.pth
|
||||
- Config: configs/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -370,7 +370,7 @@ Models:
|
||||
mIoU: 77.27
|
||||
mIoU(ms+flip): 78.88
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_40k_cityscapes-98d5d1bc.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_512x1024_80k_cityscapes/fcn_d6_r50-d16_512x1024_80k_cityscapes_20210306_115604-133c292f.pth
|
||||
- Config: configs/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -392,7 +392,7 @@ Models:
|
||||
mIoU: 76.82
|
||||
mIoU(ms+flip): 78.22
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes-1aab18ed.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_40k_cityscapes/fcn_d6_r50-d16_769x769_40k_cityscapes_20210305_185744-1aab18ed.pth
|
||||
- Config: configs/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -413,7 +413,7 @@ Models:
|
||||
mIoU: 77.04
|
||||
mIoU(ms+flip): 78.4
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes-109d88eb.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50-d16_769x769_80k_cityscapes/fcn_d6_r50-d16_769x769_80k_cityscapes_20210305_200413-109d88eb.pth
|
||||
- Config: configs/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -435,7 +435,7 @@ Models:
|
||||
mIoU: 77.36
|
||||
mIoU(ms+flip): 79.18
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes-9cf2b450.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_40k_cityscapes/fcn_d6_r101-d16_512x1024_40k_cityscapes_20210305_130337-9cf2b450.pth
|
||||
- Config: configs/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -456,7 +456,7 @@ Models:
|
||||
mIoU: 78.46
|
||||
mIoU(ms+flip): 80.42
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes-cb336445.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_512x1024_80k_cityscapes/fcn_d6_r101-d16_512x1024_80k_cityscapes_20210308_102747-cb336445.pth
|
||||
- Config: configs/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -478,7 +478,7 @@ Models:
|
||||
mIoU: 77.28
|
||||
mIoU(ms+flip): 78.95
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes-60b114e9.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_40k_cityscapes/fcn_d6_r101-d16_769x769_40k_cityscapes_20210308_102453-60b114e9.pth
|
||||
- Config: configs/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -499,7 +499,7 @@ Models:
|
||||
mIoU: 78.06
|
||||
mIoU(ms+flip): 79.58
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes-e33adc4f.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101-d16_769x769_80k_cityscapes/fcn_d6_r101-d16_769x769_80k_cityscapes_20210306_120016-e33adc4f.pth
|
||||
- Config: configs/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -521,7 +521,7 @@ Models:
|
||||
mIoU: 76.99
|
||||
mIoU(ms+flip): 79.03
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_512x1024_80k_cityscapes/fcn_d6_r50b_d16_512x1024_80k_cityscapes-6a0b62e9.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_512x1024_80k_cityscapes/fcn_d6_r50b-d16_512x1024_80k_cityscapes_20210311_125550-6a0b62e9.pth
|
||||
- Config: configs/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -543,7 +543,7 @@ Models:
|
||||
mIoU: 76.86
|
||||
mIoU(ms+flip): 78.52
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b_d16_769x769_80k_cityscapes/fcn_d6_r50b_d16_769x769_80k_cityscapes-d665f231.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r50b-d16_769x769_80k_cityscapes/fcn_d6_r50b-d16_769x769_80k_cityscapes_20210311_131012-d665f231.pth
|
||||
- Config: configs/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -565,7 +565,7 @@ Models:
|
||||
mIoU: 77.72
|
||||
mIoU(ms+flip): 79.53
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_512x1024_80k_cityscapes/fcn_d6_r101b_d16_512x1024_80k_cityscapes-3f2eb5b4.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_512x1024_80k_cityscapes/fcn_d6_r101b-d16_512x1024_80k_cityscapes_20210311_144305-3f2eb5b4.pth
|
||||
- Config: configs/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -587,7 +587,7 @@ Models:
|
||||
mIoU: 77.34
|
||||
mIoU(ms+flip): 78.91
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b_d16_769x769_80k_cityscapes/fcn_d6_r101b_d16_769x769_80k_cityscapes-c4d8bfbc.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_d6_r101b-d16_769x769_80k_cityscapes/fcn_d6_r101b-d16_769x769_80k_cityscapes_20210311_154527-c4d8bfbc.pth
|
||||
- Config: configs/fcn/fcn_r50-d8_512x512_80k_ade20k.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -752,7 +752,7 @@ Models:
|
||||
mIoU: 44.43
|
||||
mIoU(ms+flip): 45.63
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20210421_154757-b5e97937.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20210421_154757-b5e97937.pth
|
||||
- Config: configs/fcn/fcn_r101-d8_480x480_80k_pascal_context.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
@ -766,7 +766,7 @@ Models:
|
||||
mIoU: 44.13
|
||||
mIoU(ms+flip): 45.26
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20210421_163310-4711813f.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20210421_163310-4711813f.pth
|
||||
- Config: configs/fcn/fcn_r101-d8_480x480_40k_pascal_context_59.py
|
||||
In Collection: fcn
|
||||
Metadata:
|
||||
|
||||
@ -19,7 +19,7 @@
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | R-101-D8 | 512x1024 | 80000 | 5.37 | 8.64 | 76.80 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes-50245227.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230921.log.json) |
|
||||
| PSPNet | R-101-D8 | 512x1024 | 80000 | 5.34 | 8.77 | 79.46 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes-ade37931.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230919.log.json) |
|
||||
| DeepLabV3 | R-101-D8 | 512x1024 | 80000 | 5.75 | 3.86 | 80.48 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes-bc86dc84.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920.log.json) |
|
||||
| DeepLabV3+ | R-101-D8 | 512x1024 | 80000 | 6.35 | 7.87 | 80.46 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes-cc58bc8d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920.log.json) |
|
||||
| FCN | R-101-D8 | 512x1024 | 80000 | 5.37 | 8.64 | 76.80 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230921-50245227.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230921.log.json) |
|
||||
| PSPNet | R-101-D8 | 512x1024 | 80000 | 5.34 | 8.77 | 79.46 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230919-ade37931.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230919.log.json) |
|
||||
| DeepLabV3 | R-101-D8 | 512x1024 | 80000 | 5.75 | 3.86 | 80.48 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-bc86dc84.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920.log.json) |
|
||||
| DeepLabV3+ | R-101-D8 | 512x1024 | 80000 | 6.35 | 7.87 | 80.46 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-cc58bc8d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920.log.json) |
|
||||
|
||||
@ -24,7 +24,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 76.8
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes-50245227.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/fcn_r101-d8_512x1024_80k_fp16_cityscapes/fcn_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230921-50245227.pth
|
||||
- Config: configs/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes.py
|
||||
In Collection: fp16
|
||||
Metadata:
|
||||
@ -45,7 +45,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 79.46
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes-ade37931.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/pspnet_r101-d8_512x1024_80k_fp16_cityscapes/pspnet_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230919-ade37931.pth
|
||||
- Config: configs/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes.py
|
||||
In Collection: fp16
|
||||
Metadata:
|
||||
@ -66,7 +66,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 80.48
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes-bc86dc84.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-bc86dc84.pth
|
||||
- Config: configs/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes.py
|
||||
In Collection: fp16
|
||||
Metadata:
|
||||
@ -87,4 +87,4 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 80.46
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes-cc58bc8d.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/fp16/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes/deeplabv3plus_r101-d8_512x1024_80k_fp16_cityscapes_20200717_230920-cc58bc8d.pth
|
||||
|
||||
@ -34,9 +34,9 @@
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | HRNetV2p-W18-Small | 512x512 | 80000 | 3.8 | 38.66 | 31.38 | 32.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json) |
|
||||
| FCN | HRNetV2p-W18 | 512x512 | 80000 | 4.9 | 22.57 | 35.51 | 36.80 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20200614_185145-66f20cb7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20200614_185145.log.json) |
|
||||
| FCN | HRNetV2p-W18 | 512x512 | 80000 | 4.9 | 22.57 | 36.27 | 37.28 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json) |
|
||||
| FCN | HRNetV2p-W48 | 512x512 | 80000 | 8.2 | 21.23 | 41.90 | 43.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json) |
|
||||
| FCN | HRNetV2p-W18-Small | 512x512 | 160000 | - | - | 33.00 | 34.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20200614_214413-870f65ac.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20200614_214413.log.json) |
|
||||
| FCN | HRNetV2p-W18-Small | 512x512 | 160000 | - | - | 33.07 | 34.56 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json) |
|
||||
| FCN | HRNetV2p-W18 | 512x512 | 160000 | - | - | 36.79 | 38.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json) |
|
||||
| FCN | HRNetV2p-W48 | 512x512 | 160000 | - | - | 42.02 | 43.86 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json) |
|
||||
|
||||
@ -44,7 +44,7 @@
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | HRNetV2p-W18-Small | 512x512 | 20000 | 1.8 | 43.36 | 65.20 | 68.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20200617_224503-56e36088.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20200617_224503.log.json) |
|
||||
| FCN | HRNetV2p-W18-Small | 512x512 | 20000 | 1.8 | 43.36 | 65.5 | 68.89 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json) |
|
||||
| FCN | HRNetV2p-W18 | 512x512 | 20000 | 2.9 | 23.48 | 72.30 | 74.71 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json) |
|
||||
| FCN | HRNetV2p-W48 | 512x512 | 20000 | 6.2 | 22.05 | 75.87 | 78.58 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_20k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json) |
|
||||
| FCN | HRNetV2p-W18-Small | 512x512 | 40000 | - | - | 66.61 | 70.00 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_40k_voc12aug.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json) |
|
||||
|
||||
@ -198,10 +198,10 @@ Models:
|
||||
Results:
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 35.51
|
||||
mIoU(ms+flip): 36.8
|
||||
mIoU: 36.27
|
||||
mIoU(ms+flip): 37.28
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20200614_185145-66f20cb7.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth
|
||||
- Config: configs/hrnet/fcn_hr48_512x512_80k_ade20k.py
|
||||
In Collection: hrnet
|
||||
Metadata:
|
||||
@ -234,10 +234,10 @@ Models:
|
||||
Results:
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 33.0
|
||||
mIoU(ms+flip): 34.55
|
||||
mIoU: 33.07
|
||||
mIoU(ms+flip): 34.56
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20200614_214413-870f65ac.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth
|
||||
- Config: configs/hrnet/fcn_hr18_512x512_160k_ade20k.py
|
||||
In Collection: hrnet
|
||||
Metadata:
|
||||
@ -284,10 +284,10 @@ Models:
|
||||
Results:
|
||||
Dataset: Pascal VOC 2012 + Aug
|
||||
Metrics:
|
||||
mIoU: 65.2
|
||||
mIoU(ms+flip): 68.55
|
||||
mIoU: 65.5
|
||||
mIoU(ms+flip): 68.89
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20200617_224503-56e36088.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth
|
||||
- Config: configs/hrnet/fcn_hr18_512x512_20k_voc12aug.py
|
||||
In Collection: hrnet
|
||||
Metadata:
|
||||
|
||||
@ -36,7 +36,7 @@
|
||||
| NonLocal | R-50-D8 | 512x512 | 80000 | 9.1 | 21.37 | 40.75 | 42.05 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801-5ae0aa33.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_80k_ade20k/nonlocal_r50-d8_512x512_80k_ade20k_20200615_015801.log.json) |
|
||||
| NonLocal | R-101-D8 | 512x512 | 80000 | 12.6 | 13.97 | 42.90 | 44.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758-24105919.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_80k_ade20k/nonlocal_r101-d8_512x512_80k_ade20k_20200615_015758.log.json) |
|
||||
| NonLocal | R-50-D8 | 512x512 | 160000 | - | - | 42.03 | 43.04 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410-baef45e3.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r50-d8_512x512_160k_ade20k/nonlocal_r50-d8_512x512_160k_ade20k_20200616_005410.log.json) |
|
||||
| NonLocal | R-101-D8 | 512x512 | 160000 | - | - | 43.36 | 44.83 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20200616_003422-affd0f8d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20200616_003422.log.json) |
|
||||
| NonLocal | R-101-D8 | 512x512 | 160000 | - | - | 44.63 | 45.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502.log.json) |
|
||||
|
||||
### Pascal VOC 2012 + Aug
|
||||
|
||||
|
||||
@ -214,10 +214,10 @@ Models:
|
||||
Results:
|
||||
Dataset: ADE20K
|
||||
Metrics:
|
||||
mIoU: 43.36
|
||||
mIoU(ms+flip): 44.83
|
||||
mIoU: 44.63
|
||||
mIoU(ms+flip): 45.79
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20200616_003422-affd0f8d.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/nonlocal_net/nonlocal_r101-d8_512x512_160k_ade20k/nonlocal_r101-d8_512x512_160k_ade20k_20210827_221502-7881aa1a.pth
|
||||
- Config: configs/nonlocal_net/nonlocal_r50-d8_512x512_20k_voc12aug.py
|
||||
In Collection: nonlocal_net
|
||||
Metadata:
|
||||
|
||||
@ -42,9 +42,9 @@
|
||||
|
||||
| Method | Backbone | Crop Size | Batch Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------ | -------- | --------- | ---------- | ------- | -------- | -------------- | ----- | ------------: | ------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| OCRNet | R-101-D8 | 512x1024 | 8 | 40000 | - | - | 80.09 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes-02ac0f13.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json) |
|
||||
| OCRNet | R-101-D8 | 512x1024 | 16 | 40000 | 8.8 | 3.02 | 80.30 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes-db500f80.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json) |
|
||||
| OCRNet | R-101-D8 | 512x1024 | 16 | 80000 | 8.8 | 3.02 | 80.81 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes-78688424.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json) |
|
||||
| OCRNet | R-101-D8 | 512x1024 | 8 | 40000 | - | - | 80.09 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721.log.json) |
|
||||
| OCRNet | R-101-D8 | 512x1024 | 16 | 40000 | 8.8 | 3.02 | 80.30 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726.log.json) |
|
||||
| OCRNet | R-101-D8 | 512x1024 | 16 | 80000 | 8.8 | 3.02 | 80.81 | - | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421.log.json) |
|
||||
|
||||
### ADE20K
|
||||
|
||||
|
||||
@ -170,7 +170,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 80.09
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes-02ac0f13.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b8_cityscapes/ocrnet_r101-d8_512x1024_40k_b8_cityscapes_20200717_110721-02ac0f13.pth
|
||||
- Config: configs/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes.py
|
||||
In Collection: ocrnet
|
||||
Metadata:
|
||||
@ -191,7 +191,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 80.3
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes-db500f80.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_40k_b16_cityscapes/ocrnet_r101-d8_512x1024_40k_b16_cityscapes_20200723_193726-db500f80.pth
|
||||
- Config: configs/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes.py
|
||||
In Collection: ocrnet
|
||||
Metadata:
|
||||
@ -212,7 +212,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 80.81
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes-78688424.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/ocrnet/ocrnet_r101-d8_512x1024_80k_b16_cityscapes/ocrnet_r101-d8_512x1024_80k_b16_cityscapes_20200723_192421-78688424.pth
|
||||
- Config: configs/ocrnet/ocrnet_hr18s_512x512_80k_ade20k.py
|
||||
In Collection: ocrnet
|
||||
Metadata:
|
||||
|
||||
@ -21,7 +21,7 @@
|
||||
|
||||
| Method | Backbone | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Dice | config | download |
|
||||
| ----------- | --------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | ------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| FCN | UNet-S5-D16 | 584x565 | 64x64 | 42x42 | 40000 | 0.680 | - | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_64x64_40k_drive.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive-20201223_191051.log.json) |
|
||||
| FCN | UNet-S5-D16 | 584x565 | 64x64 | 42x42 | 40000 | 0.680 | - | 78.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_64x64_40k_drive.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive-20201223_191051.log.json) |
|
||||
| PSPNet | UNet-S5-D16 | 584x565 | 64x64 | 42x42 | 40000 | 0.599 | - | 78.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/pspnet_unet_s5-d16_64x64_40k_drive.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive_20201227_181818-aac73387.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_64x64_40k_drive/pspnet_unet_s5-d16_64x64_40k_drive-20201227_181818.log.json) |
|
||||
| DeepLabV3 | UNet-S5-D16 | 584x565 | 64x64 | 42x42 | 40000 | 0.596 | - | 78.69 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/deeplabv3_unet_s5-d16_64x64_40k_drive.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive_20201226_094047-0671ff20.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_64x64_40k_drive/deeplabv3_unet_s5-d16_64x64_40k_drive-20201226_094047.log.json) |
|
||||
|
||||
@ -29,7 +29,7 @@
|
||||
|
||||
| Method | Backbone | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Dice | config | download |
|
||||
| ----------- | --------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | -------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| FCN | UNet-S5-D16 | 605x700 | 128x128 | 85x85 | 40000 | 0.968 | - | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_128x128_40k_stare.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json) |
|
||||
| FCN | UNet-S5-D16 | 605x700 | 128x128 | 85x85 | 40000 | 0.968 | - | 81.02 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_128x128_40k_stare.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare-20201223_191051.log.json) |
|
||||
| PSPNet | UNet-S5-D16 | 605x700 | 128x128 | 85x85 | 40000 | 0.982 | - | 81.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/pspnet_unet_s5-d16_128x128_40k_stare.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare_20201227_181818-3c2923c4.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_stare/pspnet_unet_s5-d16_128x128_40k_stare-20201227_181818.log.json) |
|
||||
| DeepLabV3 | UNet-S5-D16 | 605x700 | 128x128 | 85x85 | 40000 | 0.999 | - | 80.93 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/deeplabv3_unet_s5-d16_128x128_40k_stare.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare_20201226_094047-93dcb93c.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_stare/deeplabv3_unet_s5-d16_128x128_40k_stare-20201226_094047.log.json) |
|
||||
|
||||
@ -37,7 +37,7 @@
|
||||
|
||||
| Method | Backbone | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Dice | config | download |
|
||||
| ----------- | --------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | -------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| FCN | UNet-S5-D16 | 960x999 | 128x128 | 85x85 | 40000 | 0.968 | - | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_128x128_40k_chase_db1.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json) |
|
||||
| FCN | UNet-S5-D16 | 960x999 | 128x128 | 85x85 | 40000 | 0.968 | - | 80.24 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_128x128_40k_chase_db1.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1-20201223_191051.log.json) |
|
||||
| PSPNet | UNet-S5-D16 | 960x999 | 128x128 | 85x85 | 40000 | 0.982 | - | 80.36 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1_20201227_181818-68d4e609.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1/pspnet_unet_s5-d16_128x128_40k_chase_db1-20201227_181818.log.json) |
|
||||
| DeepLabV3 | UNet-S5-D16 | 960x999 | 128x128 | 85x85 | 40000 | 0.999 | - | 80.47 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1_20201226_094047-4c5aefa3.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_128x128_40k_chase_db1/deeplabv3_unet_s5-d16_128x128_40k_chase_db1-20201226_094047.log.json) |
|
||||
|
||||
@ -45,6 +45,6 @@
|
||||
|
||||
| Method | Backbone | Image Size | Crop Size | Stride | Lr schd | Mem (GB) | Inf time (fps) | Dice | config | download |
|
||||
| ----------- | --------- | ---------- | --------- | -----: | ------- | -------- | -------------: | ----: | -------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| FCN | UNet-S5-D16 | 2336x3504 | 256x256 | 170x170 | 40000 | 2.525 | - | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_256x256_40k_hrf.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json) |
|
||||
| FCN | UNet-S5-D16 | 2336x3504 | 256x256 | 170x170 | 40000 | 2.525 | - | 79.45 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/fcn_unet_s5-d16_256x256_40k_hrf.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf-20201223_173724.log.json) |
|
||||
| PSPNet | UNet-S5-D16 | 2336x3504 | 256x256 | 170x170 | 40000 | 2.588 | - | 80.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/pspnet_unet_s5-d16_256x256_40k_hrf.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf_20201227_181818-fdb7e29b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/pspnet_unet_s5-d16_256x256_40k_hrf/pspnet_unet_s5-d16_256x256_40k_hrf-20201227_181818.log.json) |
|
||||
| DeepLabV3 | UNet-S5-D16 | 2336x3504 | 256x256 | 170x170 | 40000 | 2.604 | - | 80.21 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf_20201226_094047-3a1fdf85.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/unet/deeplabv3_unet_s5-d16_256x256_40k_hrf/deeplabv3_unet_s5-d16_256x256_40k_hrf-20201226_094047.log.json) |
|
||||
|
||||
@ -20,7 +20,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 78.67
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_64x64_40k_drive/unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_64x64_40k_drive/fcn_unet_s5-d16_64x64_40k_drive_20201223_191051-5daf6d3b.pth
|
||||
- Config: configs/unet/pspnet_unet_s5-d16_64x64_40k_drive.py
|
||||
In Collection: unet
|
||||
Metadata:
|
||||
@ -62,7 +62,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 81.02
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_stare/unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_stare/fcn_unet_s5-d16_128x128_40k_stare_20201223_191051-7d77e78b.pth
|
||||
- Config: configs/unet/pspnet_unet_s5-d16_128x128_40k_stare.py
|
||||
In Collection: unet
|
||||
Metadata:
|
||||
@ -104,7 +104,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 80.24
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_128x128_40k_chase_db1/unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_128x128_40k_chase_db1/fcn_unet_s5-d16_128x128_40k_chase_db1_20201223_191051-11543527.pth
|
||||
- Config: configs/unet/pspnet_unet_s5-d16_128x128_40k_chase_db1.py
|
||||
In Collection: unet
|
||||
Metadata:
|
||||
@ -146,7 +146,7 @@ Models:
|
||||
Metrics:
|
||||
mIoU: 79.45
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/unet_s5-d16_256x256_40k_hrf/unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/unet/fcn_unet_s5-d16_256x256_40k_hrf/fcn_unet_s5-d16_256x256_40k_hrf_20201223_173724-d89cf1ed.pth
|
||||
- Config: configs/unet/pspnet_unet_s5-d16_256x256_40k_hrf.py
|
||||
In Collection: unet
|
||||
Metadata:
|
||||
|
||||
@ -37,14 +37,14 @@ This script convert model from `PRETRAIN_PATH` and store the converted model in
|
||||
|
||||
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|
||||
| ------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| UPerNet | ViT-B + MLN | 512x512 | 80000 | 9.20 | 6.94 | 47.71 | 49.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_vit-b16_mln_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k-0403cee1.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json) |
|
||||
| UPerNet | ViT-B + MLN | 512x512 | 160000 | 9.20 | 7.58 | 46.75 | 48.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_vit-b16_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k-852fa768.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json) |
|
||||
| UPerNet | ViT-B + LN + MLN | 512x512 | 160000 | 9.21 | 6.82 | 47.73 | 49.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k-f444c077.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json) |
|
||||
| UPerNet | DeiT-S | 512x512 | 80000 | 4.68 | 29.85 | 42.96 | 43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k-afc93ec2.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json) |
|
||||
| UPerNet | DeiT-S | 512x512 | 160000 | 4.68 | 29.19 | 42.87 | 43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k-5110d916.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json) |
|
||||
| UPerNet | DeiT-S + MLN | 512x512 | 160000 | 5.69 | 11.18 | 43.82 | 45.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k-fb9a5dfb.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json) |
|
||||
| UPerNet | DeiT-S + LN + MLN | 512x512 | 160000 | 5.69 | 12.39 | 43.52 | 45.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k-c0cd652f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json) |
|
||||
| UPerNet | DeiT-B | 512x512 | 80000 | 7.75 | 9.69 | 45.24 | 46.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k-1e090789.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json) |
|
||||
| UPerNet | DeiT-B | 512x512 | 160000 | 7.75 | 10.39 | 45.36 | 47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k-828705d7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json) |
|
||||
| UPerNet | DeiT-B + MLN | 512x512 | 160000 | 9.21 | 7.78 | 45.46 | 47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k-4e1450f3.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json) |
|
||||
| UPerNet | DeiT-B + LN + MLN | 512x512 | 160000 | 9.21 | 7.75 | 45.37 | 47.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k-8a959c14.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json) |
|
||||
| UPerNet | ViT-B + MLN | 512x512 | 80000 | 9.20 | 6.94 | 47.71 | 49.51 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_vit-b16_mln_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/20210624_130547.log.json) |
|
||||
| UPerNet | ViT-B + MLN | 512x512 | 160000 | 9.20 | 7.58 | 46.75 | 48.46 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_vit-b16_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/20210623_192432.log.json) |
|
||||
| UPerNet | ViT-B + LN + MLN | 512x512 | 160000 | 9.21 | 6.82 | 47.73 | 49.95 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/20210621_172828.log.json) |
|
||||
| UPerNet | DeiT-S | 512x512 | 80000 | 4.68 | 29.85 | 42.96 | 43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/20210624_095228.log.json) |
|
||||
| UPerNet | DeiT-S | 512x512 | 160000 | 4.68 | 29.19 | 42.87 | 43.79 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/20210621_160903.log.json) |
|
||||
| UPerNet | DeiT-S + MLN | 512x512 | 160000 | 5.69 | 11.18 | 43.82 | 45.07 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/20210621_161021.log.json) |
|
||||
| UPerNet | DeiT-S + LN + MLN | 512x512 | 160000 | 5.69 | 12.39 | 43.52 | 45.01 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/20210621_161021.log.json) |
|
||||
| UPerNet | DeiT-B | 512x512 | 80000 | 7.75 | 9.69 | 45.24 | 46.73 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_512x512_80k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/20210624_130529.log.json) |
|
||||
| UPerNet | DeiT-B | 512x512 | 160000 | 7.75 | 10.39 | 45.36 | 47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/20210621_180100.log.json) |
|
||||
| UPerNet | DeiT-B + MLN | 512x512 | 160000 | 9.21 | 7.78 | 45.46 | 47.16 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/20210621_191949.log.json) |
|
||||
| UPerNet | DeiT-B + LN + MLN | 512x512 | 160000 | 9.21 | 7.75 | 45.37 | 47.23 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/20210623_153535.log.json) |
|
||||
|
||||
@ -25,7 +25,7 @@ Models:
|
||||
mIoU: 47.71
|
||||
mIoU(ms+flip): 49.51
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k-0403cee1.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_80k_ade20k/upernet_vit-b16_mln_512x512_80k_ade20k_20210624_130547-0403cee1.pth
|
||||
- Config: configs/vit/upernet_vit-b16_mln_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -47,7 +47,7 @@ Models:
|
||||
mIoU: 46.75
|
||||
mIoU(ms+flip): 48.46
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k-852fa768.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_mln_512x512_160k_ade20k/upernet_vit-b16_mln_512x512_160k_ade20k_20210624_130547-852fa768.pth
|
||||
- Config: configs/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -69,7 +69,7 @@ Models:
|
||||
mIoU: 47.73
|
||||
mIoU(ms+flip): 49.95
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k-f444c077.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_vit-b16_ln_mln_512x512_160k_ade20k/upernet_vit-b16_ln_mln_512x512_160k_ade20k_20210621_172828-f444c077.pth
|
||||
- Config: configs/vit/upernet_deit-s16_512x512_80k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -91,7 +91,7 @@ Models:
|
||||
mIoU: 42.96
|
||||
mIoU(ms+flip): 43.79
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k-afc93ec2.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_80k_ade20k/upernet_deit-s16_512x512_80k_ade20k_20210624_095228-afc93ec2.pth
|
||||
- Config: configs/vit/upernet_deit-s16_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -113,7 +113,7 @@ Models:
|
||||
mIoU: 42.87
|
||||
mIoU(ms+flip): 43.79
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k-5110d916.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_512x512_160k_ade20k/upernet_deit-s16_512x512_160k_ade20k_20210621_160903-5110d916.pth
|
||||
- Config: configs/vit/upernet_deit-s16_mln_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -135,7 +135,7 @@ Models:
|
||||
mIoU: 43.82
|
||||
mIoU(ms+flip): 45.07
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k-fb9a5dfb.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_mln_512x512_160k_ade20k/upernet_deit-s16_mln_512x512_160k_ade20k_20210621_161021-fb9a5dfb.pth
|
||||
- Config: configs/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -157,7 +157,7 @@ Models:
|
||||
mIoU: 43.52
|
||||
mIoU(ms+flip): 45.01
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k-c0cd652f.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-s16_ln_mln_512x512_160k_ade20k/upernet_deit-s16_ln_mln_512x512_160k_ade20k_20210621_161021-c0cd652f.pth
|
||||
- Config: configs/vit/upernet_deit-b16_512x512_80k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -179,7 +179,7 @@ Models:
|
||||
mIoU: 45.24
|
||||
mIoU(ms+flip): 46.73
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k-1e090789.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_80k_ade20k/upernet_deit-b16_512x512_80k_ade20k_20210624_130529-1e090789.pth
|
||||
- Config: configs/vit/upernet_deit-b16_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -201,7 +201,7 @@ Models:
|
||||
mIoU: 45.36
|
||||
mIoU(ms+flip): 47.16
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k-828705d7.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_512x512_160k_ade20k/upernet_deit-b16_512x512_160k_ade20k_20210621_180100-828705d7.pth
|
||||
- Config: configs/vit/upernet_deit-b16_mln_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -223,7 +223,7 @@ Models:
|
||||
mIoU: 45.46
|
||||
mIoU(ms+flip): 47.16
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k-4e1450f3.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_mln_512x512_160k_ade20k/upernet_deit-b16_mln_512x512_160k_ade20k_20210621_191949-4e1450f3.pth
|
||||
- Config: configs/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k.py
|
||||
In Collection: vit
|
||||
Metadata:
|
||||
@ -245,4 +245,4 @@ Models:
|
||||
mIoU: 45.37
|
||||
mIoU(ms+flip): 47.23
|
||||
Task: Semantic Segmentation
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k-8a959c14.pth
|
||||
Weights: https://download.openmmlab.com/mmsegmentation/v0.5/vit/upernet_deit-b16_ln_mln_512x512_160k_ade20k/upernet_deit-b16_ln_mln_512x512_160k_ade20k_20210623_153535-8a959c14.pth
|
||||
|
||||
@ -8,6 +8,6 @@ line_length = 79
|
||||
multi_line_output = 0
|
||||
known_standard_library = setuptools
|
||||
known_first_party = mmseg
|
||||
known_third_party = PIL,cityscapesscripts,cv2,detail,matplotlib,mmcv,numpy,onnxruntime,oss2,packaging,prettytable,pytest,scipy,seaborn,torch,ts
|
||||
known_third_party = PIL,cityscapesscripts,cv2,detail,matplotlib,mmcv,numpy,onnxruntime,packaging,prettytable,pytest,scipy,seaborn,torch,ts
|
||||
no_lines_before = STDLIB,LOCALFOLDER
|
||||
default_section = THIRDPARTY
|
||||
|
||||
@ -1,7 +1,9 @@
|
||||
# Copyright (c) OpenMMLab. All rights reserved.
|
||||
import argparse
|
||||
import os
|
||||
import os.path as osp
|
||||
import shutil
|
||||
import time
|
||||
import warnings
|
||||
|
||||
import mmcv
|
||||
@ -21,6 +23,10 @@ def parse_args():
|
||||
description='mmseg test (and eval) a model')
|
||||
parser.add_argument('config', help='test config file path')
|
||||
parser.add_argument('checkpoint', help='checkpoint file')
|
||||
parser.add_argument(
|
||||
'--work-dir',
|
||||
help=('if specified, the evaluation metric results will be dumped'
|
||||
'into the directory as json'))
|
||||
parser.add_argument(
|
||||
'--aug-test', action='store_true', help='Use Flip and Multi scale aug')
|
||||
parser.add_argument('--out', help='output result file in pickle format')
|
||||
@ -108,6 +114,13 @@ def main():
|
||||
distributed = True
|
||||
init_dist(args.launcher, **cfg.dist_params)
|
||||
|
||||
rank, _ = get_dist_info()
|
||||
# allows not to create
|
||||
if args.work_dir is not None and rank == 0:
|
||||
mmcv.mkdir_or_exist(osp.abspath(args.work_dir))
|
||||
timestamp = time.strftime('%Y%m%d_%H%M%S', time.localtime())
|
||||
json_file = osp.join(args.work_dir, f'eval_{timestamp}.json')
|
||||
|
||||
# build the dataloader
|
||||
# TODO: support multiple images per gpu (only minor changes are needed)
|
||||
dataset = build_dataset(cfg.data.test)
|
||||
@ -202,10 +215,13 @@ def main():
|
||||
print(f'\nwriting results to {args.out}')
|
||||
mmcv.dump(results, args.out)
|
||||
if args.eval:
|
||||
dataset.evaluate(results, args.eval, **eval_kwargs)
|
||||
if tmpdir is not None and eval_on_format_results:
|
||||
# remove tmp dir when cityscapes evaluation
|
||||
shutil.rmtree(tmpdir)
|
||||
metric = dataset.evaluate(results, args.eval, **eval_kwargs)
|
||||
metric_dict = dict(config=args.config, metric=metric)
|
||||
if args.work_dir is not None and rank == 0:
|
||||
mmcv.dump(metric_dict, json_file, indent=4)
|
||||
if tmpdir is not None and eval_on_format_results:
|
||||
# remove tmp dir when cityscapes evaluation
|
||||
shutil.rmtree(tmpdir)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user