Skip to content

M
mmaction2

openvinotoolkit / mmaction2
大约 1 年 前同步成功

通知 2
Star 5
Fork 3
M
mmaction2

体验新版 GitCode，发现更多精彩内容 >>

提交 6b7f9dbb 编写于 作者: L lixuanyi
浏览文件
操作

update readme 

Signed-off-by: Nlixuanyi <lixuanyi@sensetime.com>
上级 e9a9fd14
隐藏空白更改
内联 并排
Showing with 23 addition and 19 deletion
configs/localization/bmn/README.md
浏览文件 @ 6b7f9dbb
# BMN
|config | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log|
|-|-|-|-|-|-|- | -|
|bmn_400x100_9e_2x8_activitynet_feature | None |75.28|67.22|5420|3.27|[ckpt]()| [log]()|
......@@ -23,7 +24,7 @@ You can use the following command to train a model.
python tools/train.py ${CONFIG_FILE} [optional arguments]
# Example: train BMN on ActivityNet features dataset
python tools/train.py config/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py
python tools/train.py configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py
```
## Test
......@@ -33,5 +34,5 @@ python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
# Example: test BMN on ActivityNet feature dataset
# Note: If evaluated, then please make sure the annotation file for test data contains groundtruth.
python tools/test.py config/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth --eval AR@AN --out results.json
python tools/test.py configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth --eval AR@AN --out results.json
```
configs/localization/bsn/README.md
浏览文件 @ 6b7f9dbb
# BSN
|config | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log|
|-|-|-|-|-|-|- | -|
|bsn_400x100_1x16_20e_activitynet_feature | None |74.91|66.31|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem]() [ckpt_pem]| [log_tem]() [log_pem]()|
|bsn_400x100_1x16_20e_activitynet_feature | None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem]() [ckpt_pem]| [log_tem]() [log_pem]()|
## Preparation
### Data
......@@ -24,29 +25,29 @@ You can use the following commands to train a model.
# TEM Train
python tools/train.py ${CONFIG_FILE} [optional arguments]
# Example: train BSN(TEM) on ActivityNet features dataset
python tools/train.py config/localization/bsn/bsn_400x100_1x16_20e_activitynet_feature.py
python tools/train.py configs/localization/bsn/bsn_400x100_1x16_20e_activitynet_feature.py
# TEM Inference
# Note: This could not be evaluated.
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
# Example: Inference BSN(TEM) with trained model.
python tools/test.py config/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth
python tools/test.py configs/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth
# PGM
python tools/bsn_proposal_generation.py ${CONFIG_FILE} [--mode ${MODE}]
# Example: Inference BSN(PGM)
python tools/bsn_proposal_generation.py config/localization/bsn/bsn_pgm_400x100_activitynet_feature.py --mode train
python tools/bsn_proposal_generation.py configs/localization/bsn/bsn_pgm_400x100_activitynet_feature.py --mode train
# PEM Train
python tools/train.py ${CONFIG_FILE} [optional arguments]
# Example: train BSN(PEM) on PGM results.
python tools/train.py config/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature.py
python tools/train.py configs/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature.py
# PEM Inference
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
# Example: Inference BSN(PEM) with evaluation metric 'AR@AN' and output the results.
# Note: If evaluated, then please make sure the annotation file for test data contains groundtruth.
python tools/test.py config/localization/bsn/bsn_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth --eval AR@AN --out results.json
python tools/test.py configs/localization/bsn/bsn_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth --eval AR@AN --out results.json
```
## Test
......@@ -55,16 +56,16 @@ python tools/test.py config/localization/bsn/bsn_400x100_1x16_20e_activitynet_fe
# Note: This could not be evaluated.
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
# Example: Test a TEM model on ActivityNet dataset.
python tools/test.py config/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth
python tools/test.py configs/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth
# PGM
python tools/bsn_proposal_generation.py ${CONFIG_FILE} [--mode ${MODE}]
# Example:
python tools/bsn_proposal_generation.py config/localization/bsn/bsn_pgm_400x100_activitynet_feature.py --mode test
python tools/bsn_proposal_generation.py configs/localization/bsn/bsn_pgm_400x100_activitynet_feature.py --mode test
# PEM
python tools/test.py ${CONFIG_FILE} ${CHECKPOINT_FILE} [optional arguments]
# Example: Test a PEM model with with evaluation metric 'AR@AN' and output the results.
# Note: If evaluated, then please make sure the annotation file for test data contains groundtruth.
python tools/test.py config/localization/bsn/bsn_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth --eval AR@AN --out results.json
python tools/test.py configs/localization/bsn/bsn_400x100_1x16_20e_activitynet_feature.py checkpoints/SOME_CHECKPOINT.pth --eval AR@AN --out results.json
```
configs/recognition/r2plus1d/README.md
浏览文件 @ 6b7f9dbb
# R2plus1D
config | pretrain | top1 acc| top5 acc | gpu_mem(M) | iter time(s) | ckpt | log
-|-|-|-|-|-|- | -
r2plus1d_r34_3d_8x8x1_180e_kinetics400_rgb | None |68.68|88.36|5014|0.68|[ckpt]()| [log]()
r2plus1d_r34_3d_32x2x1__180e_kinetics400_rgb|None|74.60|91.59|9003|1.23| [ckpt]() | [log]()
|config | pretrain | top1 acc| top5 acc | gpu_mem(M) | iter time(s) | ckpt | log|
|-|-|-|-|-|-|- | -|
|r2plus1d_r34_3d_8x8x1_180e_kinetics400_rgb | None |68.68|88.36|5014|0.68|[ckpt]()| [log]()|
|r2plus1d_r34_3d_32x2x1__180e_kinetics400_rgb|None|74.60|91.59|9003|1.23| [ckpt]() | [log]()|
configs/recognition/slowfast/README.md
浏览文件 @ 6b7f9dbb
# Slowfast
config | pretrain | top1 acc| top5 acc | gpu_mem(M) | iter time(s) | ckpt | log
-|-|-|-|-|-|- | -
slowfast_r50_3d_4x16x1_256e_kinetics400_rgb | None |75.3|92.2|6250|0.826|[ckpt]()| [log]()
slowfast_r50_3d_8x8x1_256e_kinetics400_rgb|None|76.36|92.56|9159|1.032| [ckpt]() | [log]()
|config | pretrain | top1 acc| top5 acc | gpu_mem(M) | iter time(s) | ckpt | log|
|-|-|-|-|-|-|- | -|
|slowfast_r50_3d_4x16x1_256e_kinetics400_rgb | None |75.3|92.2|6250|0.826|[ckpt]()| [log]()|
|slowfast_r50_3d_8x8x1_256e_kinetics400_rgb|None|76.36|92.56|9159|1.032| [ckpt]() | [log]()|
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或