Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add BSN / BMN results with feature extracted by mmaction #99

Closed
wants to merge 1 commit into from
Closed

Add BSN / BMN results with feature extracted by mmaction #99

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions configs/localization/bmn/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,17 @@

### ActivityNet feature

|config | gpus | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|[bmn_400x100_9e_2x8_activitynet_feature](/configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py) |2| None |75.28|67.22|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature_20200619-42a3b111.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log.json)|
|config |feature | gpus | pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:-:|
|[bmn_400x100_9e_2x8_activitynet_feature](/configs/localization/bmn/bmn_400x100_2x8_9e_activitynet_feature.py) |cuhk_mean_100 |2| None |75.28|67.22|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature_20200619-42a3b111.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log)| [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_9e_activitynet_feature/bmn_400x100_9e_activitynet_feature.log.json)|
| |mmaction_video |2| None |75.43|67.22|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_video/bmn_400x100_2x8_9e_mmaction_video_20200809-c9fd14d2.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_video/bmn_400x100_2x8_9e_mmaction_video_20200809.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_video/bmn_400x100_2x8_9e_mmaction_video_20200809.json) |
| |mmaction_clip |2| None |75.35|67.38|5420|3.27|[ckpt](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_clip/bmn_400x100_2x8_9e_mmaction_clip_20200809-10d803ce.pth)| [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_clip/bmn_400x100_2x8_9e_mmaction_clip_20200809.log) | [json](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bmn/bmn_400x100_2x8_9e_mmaction_clip/bmn_400x100_2x8_9e_mmaction_clip_20200809.json) |

Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. For feature column, cuhk_mean_100 denotes the widely used cuhk activitynet feature extracted by [anet2016-cuhk](https://github.com/yjxiong/anet2016-cuhk), mmaction_video and mmaction_clip denote feature extracted by mmaction, with video-level activitynet finetuned model or clip-level activitynet finetuned model respectively.

For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md).

Expand Down
9 changes: 6 additions & 3 deletions configs/localization/bsn/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,17 @@

### ActivityNet feature

|config | gpus| pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|
|bsn_400x100_1x16_20e_activitynet_feature |1| None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature_20200619-cd6accc3.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature_20200619-6111891d.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log)| [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log.json)|
|config |feature | gpus| pretrain | AR@100| AUC | gpu_mem(M) | iter time(s) | ckpt | log| json|
|:--|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:--:|:-:|
|bsn_400x100_1x16_20e_activitynet_feature |cuhk_mean_100 |1| None |74.65|66.45|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature_20200619-cd6accc3.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature_20200619-6111891d.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log)| [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_activitynet_feature/bsn_tem_400x100_1x16_20e_activitynet_feature.log.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_activitynet_feature/bsn_pem_400x100_1x16_20e_activitynet_feature.log.json)|
| |mmaction_video |1| None |74.93|66.74|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_video/bsn_tem_400x100_1x16_20e_mmaction_video_20200809-ad6ec626.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_video/bsn_pem_400x100_1x16_20e_mmaction_video_20200809-aa861b26.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_video/bsn_tem_400x100_1x16_20e_mmaction_video_20200809.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_video/bsn_pem_400x100_1x16_20e_mmaction_video_20200809.log) | [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_video/bsn_tem_400x100_1x16_20e_mmaction_video_20200809.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_video/bsn_pem_400x100_1x16_20e_mmaction_video_20200809.json) |
| |mmaction_clip |1| None |75.19|66.81|41(TEM)+25(PEM)|0.074(TEM)+0.036(PEM)|[ckpt_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_clip/bsn_tem_400x100_1x16_20e_mmaction_clip_20200809-0a563554.pth) [ckpt_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_clip/bsn_pem_400x100_1x16_20e_mmaction_clip_20200809-e32f61e6.pth)| [log_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_clip/bsn_tem_400x100_1x16_20e_mmaction_clip_20200809.log) [log_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_clip/bsn_pem_400x100_1x16_20e_mmaction_clip_20200809.log) | [json_tem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_tem_400x100_1x16_20e_mmaction_clip/bsn_tem_400x100_1x16_20e_mmaction_clip_20200809.json) [json_pem](https://openmmlab.oss-accelerate.aliyuncs.com/mmaction/localization/bsn/bsn_pem_400x100_1x16_20e_mmaction_clip/bsn_pem_400x100_1x16_20e_mmaction_clip_20200809.json) |

Notes:
1. The **gpus** indicates the number of gpu we used to get the checkpoint.
According to the [Linear Scaling Rule](https://arxiv.org/abs/1706.02677), you may set the learning rate proportional to the batch size if you use different GPUs or videos per GPU,
e.g., lr=0.01 for 4 GPUs * 2 video/gpu and lr=0.08 for 16 GPUs * 4 video/gpu.
2. For feature column, cuhk_mean_100 denotes the widely used cuhk activitynet feature extracted by [anet2016-cuhk](https://github.com/yjxiong/anet2016-cuhk), mmaction_video and mmaction_clip denote feature extracted by mmaction, with video-level activitynet finetuned model or clip-level activitynet finetuned model respectively.

For more details on data preparation, you can refer to ActivityNet feature in [Data Preparation](/docs/data_preparation.md).

Expand Down